Combining transformers with CNN for multi-focus image fusion
Recently, deep convolutional neural network (CNN) based methods for multi-focus image fusion have achieved adequate performance. However, most of them cannot obtain spatially continuous results, especially in smooth regions and edges between focused and defocused regions. In this paper, we propose a...
Ausführliche Beschreibung
Autor*in: |
Duan, Zhao [verfasserIn] Luo, Xiaoliu [verfasserIn] Zhang, Taiping [verfasserIn] |
---|
Format: |
E-Artikel |
---|---|
Sprache: |
Englisch |
Erschienen: |
2023 |
---|
Schlagwörter: |
---|
Übergeordnetes Werk: |
Enthalten in: Expert systems with applications - Amsterdam [u.a.] : Elsevier Science, 1990, 235 |
---|---|
Übergeordnetes Werk: |
volume:235 |
DOI / URN: |
10.1016/j.eswa.2023.121156 |
---|
Katalog-ID: |
ELV065244761 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | ELV065244761 | ||
003 | DE-627 | ||
005 | 20231205153529.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231023s2023 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1016/j.eswa.2023.121156 |2 doi | |
035 | |a (DE-627)ELV065244761 | ||
035 | |a (ELSEVIER)S0957-4174(23)01658-5 | ||
040 | |a DE-627 |b ger |c DE-627 |e rda | ||
041 | |a eng | ||
082 | 0 | 4 | |a 004 |q VZ |
084 | |a 54.72 |2 bkl | ||
100 | 1 | |a Duan, Zhao |e verfasserin |0 (orcid)0000-0001-6783-7727 |4 aut | |
245 | 1 | 0 | |a Combining transformers with CNN for multi-focus image fusion |
264 | 1 | |c 2023 | |
336 | |a nicht spezifiziert |b zzz |2 rdacontent | ||
337 | |a Computermedien |b c |2 rdamedia | ||
338 | |a Online-Ressource |b cr |2 rdacarrier | ||
520 | |a Recently, deep convolutional neural network (CNN) based methods for multi-focus image fusion have achieved adequate performance. However, most of them cannot obtain spatially continuous results, especially in smooth regions and edges between focused and defocused regions. In this paper, we propose a novel end-to-end method, which merits both Transformers and CNNs, as a strong alternative for multi-focus image fusion task. Transformer has advantages over a CNN in that it can extract global features. It is able to make the fusion results to be spatially consistent. The proposed architecture consists of CNN and transformer branches, where transformer branches take feature map patches as inputs and leverages the transformer to propagate global contexts among patches. Moreover, in order to improve feature representation, we introduce online knowledge distillation learning strategy (KDL). The strategy achieves better interactions between global features and local features. Specifically, we design hard target and soft target by simply yet effectively ensembling outputs of two branches, which are used to supervise CNN and transformer branches. The experiments demonstrate the superiority of our proposed architecture and achieve competitive results with state-of-the-art methods. | ||
650 | 4 | |a Multi-focus image fusion | |
650 | 4 | |a Transformers | |
650 | 4 | |a Knowledge distillation | |
650 | 4 | |a CNNs | |
700 | 1 | |a Luo, Xiaoliu |e verfasserin |0 (orcid)0000-0002-2365-4950 |4 aut | |
700 | 1 | |a Zhang, Taiping |e verfasserin |0 (orcid)0000-0001-9891-4203 |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Expert systems with applications |d Amsterdam [u.a.] : Elsevier Science, 1990 |g 235 |h Online-Ressource |w (DE-627)320577961 |w (DE-600)2017237-0 |w (DE-576)11481807X |7 nnns |
773 | 1 | 8 | |g volume:235 |
912 | |a GBV_USEFLAG_U | ||
912 | |a GBV_ELV | ||
912 | |a SYSFLAG_U | ||
912 | |a GBV_ILN_20 | ||
912 | |a GBV_ILN_22 | ||
912 | |a GBV_ILN_23 | ||
912 | |a GBV_ILN_24 | ||
912 | |a GBV_ILN_31 | ||
912 | |a GBV_ILN_32 | ||
912 | |a GBV_ILN_40 | ||
912 | |a GBV_ILN_60 | ||
912 | |a GBV_ILN_62 | ||
912 | |a GBV_ILN_65 | ||
912 | |a GBV_ILN_69 | ||
912 | |a GBV_ILN_70 | ||
912 | |a GBV_ILN_73 | ||
912 | |a GBV_ILN_74 | ||
912 | |a GBV_ILN_90 | ||
912 | |a GBV_ILN_95 | ||
912 | |a GBV_ILN_100 | ||
912 | |a GBV_ILN_101 | ||
912 | |a GBV_ILN_105 | ||
912 | |a GBV_ILN_110 | ||
912 | |a GBV_ILN_150 | ||
912 | |a GBV_ILN_151 | ||
912 | |a GBV_ILN_187 | ||
912 | |a GBV_ILN_213 | ||
912 | |a GBV_ILN_224 | ||
912 | |a GBV_ILN_230 | ||
912 | |a GBV_ILN_370 | ||
912 | |a GBV_ILN_602 | ||
912 | |a GBV_ILN_702 | ||
912 | |a GBV_ILN_2001 | ||
912 | |a GBV_ILN_2003 | ||
912 | |a GBV_ILN_2004 | ||
912 | |a GBV_ILN_2005 | ||
912 | |a GBV_ILN_2007 | ||
912 | |a GBV_ILN_2008 | ||
912 | |a GBV_ILN_2009 | ||
912 | |a GBV_ILN_2010 | ||
912 | |a GBV_ILN_2011 | ||
912 | |a GBV_ILN_2014 | ||
912 | |a GBV_ILN_2015 | ||
912 | |a GBV_ILN_2020 | ||
912 | |a GBV_ILN_2021 | ||
912 | |a GBV_ILN_2025 | ||
912 | |a GBV_ILN_2026 | ||
912 | |a GBV_ILN_2027 | ||
912 | |a GBV_ILN_2034 | ||
912 | |a GBV_ILN_2044 | ||
912 | |a GBV_ILN_2048 | ||
912 | |a GBV_ILN_2049 | ||
912 | |a GBV_ILN_2050 | ||
912 | |a GBV_ILN_2055 | ||
912 | |a GBV_ILN_2056 | ||
912 | |a GBV_ILN_2059 | ||
912 | |a GBV_ILN_2061 | ||
912 | |a GBV_ILN_2064 | ||
912 | |a GBV_ILN_2088 | ||
912 | |a GBV_ILN_2106 | ||
912 | |a GBV_ILN_2110 | ||
912 | |a GBV_ILN_2111 | ||
912 | |a GBV_ILN_2112 | ||
912 | |a GBV_ILN_2122 | ||
912 | |a GBV_ILN_2129 | ||
912 | |a GBV_ILN_2143 | ||
912 | |a GBV_ILN_2152 | ||
912 | |a GBV_ILN_2153 | ||
912 | |a GBV_ILN_2190 | ||
912 | |a GBV_ILN_2232 | ||
912 | |a GBV_ILN_2336 | ||
912 | |a GBV_ILN_2470 | ||
912 | |a GBV_ILN_2507 | ||
912 | |a GBV_ILN_4035 | ||
912 | |a GBV_ILN_4037 | ||
912 | |a GBV_ILN_4112 | ||
912 | |a GBV_ILN_4125 | ||
912 | |a GBV_ILN_4242 | ||
912 | |a GBV_ILN_4249 | ||
912 | |a GBV_ILN_4251 | ||
912 | |a GBV_ILN_4305 | ||
912 | |a GBV_ILN_4306 | ||
912 | |a GBV_ILN_4307 | ||
912 | |a GBV_ILN_4313 | ||
912 | |a GBV_ILN_4322 | ||
912 | |a GBV_ILN_4323 | ||
912 | |a GBV_ILN_4324 | ||
912 | |a GBV_ILN_4325 | ||
912 | |a GBV_ILN_4326 | ||
912 | |a GBV_ILN_4333 | ||
912 | |a GBV_ILN_4334 | ||
912 | |a GBV_ILN_4338 | ||
912 | |a GBV_ILN_4393 | ||
912 | |a GBV_ILN_4700 | ||
936 | b | k | |a 54.72 |j Künstliche Intelligenz |q VZ |
951 | |a AR | ||
952 | |d 235 |
author_variant |
z d zd x l xl t z tz |
---|---|
matchkey_str |
duanzhaoluoxiaoliuzhangtaiping:2023----:obnntasomrwtcnomlio |
hierarchy_sort_str |
2023 |
bklnumber |
54.72 |
publishDate |
2023 |
allfields |
10.1016/j.eswa.2023.121156 doi (DE-627)ELV065244761 (ELSEVIER)S0957-4174(23)01658-5 DE-627 ger DE-627 rda eng 004 VZ 54.72 bkl Duan, Zhao verfasserin (orcid)0000-0001-6783-7727 aut Combining transformers with CNN for multi-focus image fusion 2023 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Recently, deep convolutional neural network (CNN) based methods for multi-focus image fusion have achieved adequate performance. However, most of them cannot obtain spatially continuous results, especially in smooth regions and edges between focused and defocused regions. In this paper, we propose a novel end-to-end method, which merits both Transformers and CNNs, as a strong alternative for multi-focus image fusion task. Transformer has advantages over a CNN in that it can extract global features. It is able to make the fusion results to be spatially consistent. The proposed architecture consists of CNN and transformer branches, where transformer branches take feature map patches as inputs and leverages the transformer to propagate global contexts among patches. Moreover, in order to improve feature representation, we introduce online knowledge distillation learning strategy (KDL). The strategy achieves better interactions between global features and local features. Specifically, we design hard target and soft target by simply yet effectively ensembling outputs of two branches, which are used to supervise CNN and transformer branches. The experiments demonstrate the superiority of our proposed architecture and achieve competitive results with state-of-the-art methods. Multi-focus image fusion Transformers Knowledge distillation CNNs Luo, Xiaoliu verfasserin (orcid)0000-0002-2365-4950 aut Zhang, Taiping verfasserin (orcid)0000-0001-9891-4203 aut Enthalten in Expert systems with applications Amsterdam [u.a.] : Elsevier Science, 1990 235 Online-Ressource (DE-627)320577961 (DE-600)2017237-0 (DE-576)11481807X nnns volume:235 GBV_USEFLAG_U GBV_ELV SYSFLAG_U GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_187 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2007 GBV_ILN_2008 GBV_ILN_2009 GBV_ILN_2010 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2026 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2055 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2088 GBV_ILN_2106 GBV_ILN_2110 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_2470 GBV_ILN_2507 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4242 GBV_ILN_4249 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4338 GBV_ILN_4393 GBV_ILN_4700 54.72 Künstliche Intelligenz VZ AR 235 |
spelling |
10.1016/j.eswa.2023.121156 doi (DE-627)ELV065244761 (ELSEVIER)S0957-4174(23)01658-5 DE-627 ger DE-627 rda eng 004 VZ 54.72 bkl Duan, Zhao verfasserin (orcid)0000-0001-6783-7727 aut Combining transformers with CNN for multi-focus image fusion 2023 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Recently, deep convolutional neural network (CNN) based methods for multi-focus image fusion have achieved adequate performance. However, most of them cannot obtain spatially continuous results, especially in smooth regions and edges between focused and defocused regions. In this paper, we propose a novel end-to-end method, which merits both Transformers and CNNs, as a strong alternative for multi-focus image fusion task. Transformer has advantages over a CNN in that it can extract global features. It is able to make the fusion results to be spatially consistent. The proposed architecture consists of CNN and transformer branches, where transformer branches take feature map patches as inputs and leverages the transformer to propagate global contexts among patches. Moreover, in order to improve feature representation, we introduce online knowledge distillation learning strategy (KDL). The strategy achieves better interactions between global features and local features. Specifically, we design hard target and soft target by simply yet effectively ensembling outputs of two branches, which are used to supervise CNN and transformer branches. The experiments demonstrate the superiority of our proposed architecture and achieve competitive results with state-of-the-art methods. Multi-focus image fusion Transformers Knowledge distillation CNNs Luo, Xiaoliu verfasserin (orcid)0000-0002-2365-4950 aut Zhang, Taiping verfasserin (orcid)0000-0001-9891-4203 aut Enthalten in Expert systems with applications Amsterdam [u.a.] : Elsevier Science, 1990 235 Online-Ressource (DE-627)320577961 (DE-600)2017237-0 (DE-576)11481807X nnns volume:235 GBV_USEFLAG_U GBV_ELV SYSFLAG_U GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_187 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2007 GBV_ILN_2008 GBV_ILN_2009 GBV_ILN_2010 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2026 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2055 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2088 GBV_ILN_2106 GBV_ILN_2110 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_2470 GBV_ILN_2507 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4242 GBV_ILN_4249 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4338 GBV_ILN_4393 GBV_ILN_4700 54.72 Künstliche Intelligenz VZ AR 235 |
allfields_unstemmed |
10.1016/j.eswa.2023.121156 doi (DE-627)ELV065244761 (ELSEVIER)S0957-4174(23)01658-5 DE-627 ger DE-627 rda eng 004 VZ 54.72 bkl Duan, Zhao verfasserin (orcid)0000-0001-6783-7727 aut Combining transformers with CNN for multi-focus image fusion 2023 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Recently, deep convolutional neural network (CNN) based methods for multi-focus image fusion have achieved adequate performance. However, most of them cannot obtain spatially continuous results, especially in smooth regions and edges between focused and defocused regions. In this paper, we propose a novel end-to-end method, which merits both Transformers and CNNs, as a strong alternative for multi-focus image fusion task. Transformer has advantages over a CNN in that it can extract global features. It is able to make the fusion results to be spatially consistent. The proposed architecture consists of CNN and transformer branches, where transformer branches take feature map patches as inputs and leverages the transformer to propagate global contexts among patches. Moreover, in order to improve feature representation, we introduce online knowledge distillation learning strategy (KDL). The strategy achieves better interactions between global features and local features. Specifically, we design hard target and soft target by simply yet effectively ensembling outputs of two branches, which are used to supervise CNN and transformer branches. The experiments demonstrate the superiority of our proposed architecture and achieve competitive results with state-of-the-art methods. Multi-focus image fusion Transformers Knowledge distillation CNNs Luo, Xiaoliu verfasserin (orcid)0000-0002-2365-4950 aut Zhang, Taiping verfasserin (orcid)0000-0001-9891-4203 aut Enthalten in Expert systems with applications Amsterdam [u.a.] : Elsevier Science, 1990 235 Online-Ressource (DE-627)320577961 (DE-600)2017237-0 (DE-576)11481807X nnns volume:235 GBV_USEFLAG_U GBV_ELV SYSFLAG_U GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_187 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2007 GBV_ILN_2008 GBV_ILN_2009 GBV_ILN_2010 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2026 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2055 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2088 GBV_ILN_2106 GBV_ILN_2110 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_2470 GBV_ILN_2507 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4242 GBV_ILN_4249 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4338 GBV_ILN_4393 GBV_ILN_4700 54.72 Künstliche Intelligenz VZ AR 235 |
allfieldsGer |
10.1016/j.eswa.2023.121156 doi (DE-627)ELV065244761 (ELSEVIER)S0957-4174(23)01658-5 DE-627 ger DE-627 rda eng 004 VZ 54.72 bkl Duan, Zhao verfasserin (orcid)0000-0001-6783-7727 aut Combining transformers with CNN for multi-focus image fusion 2023 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Recently, deep convolutional neural network (CNN) based methods for multi-focus image fusion have achieved adequate performance. However, most of them cannot obtain spatially continuous results, especially in smooth regions and edges between focused and defocused regions. In this paper, we propose a novel end-to-end method, which merits both Transformers and CNNs, as a strong alternative for multi-focus image fusion task. Transformer has advantages over a CNN in that it can extract global features. It is able to make the fusion results to be spatially consistent. The proposed architecture consists of CNN and transformer branches, where transformer branches take feature map patches as inputs and leverages the transformer to propagate global contexts among patches. Moreover, in order to improve feature representation, we introduce online knowledge distillation learning strategy (KDL). The strategy achieves better interactions between global features and local features. Specifically, we design hard target and soft target by simply yet effectively ensembling outputs of two branches, which are used to supervise CNN and transformer branches. The experiments demonstrate the superiority of our proposed architecture and achieve competitive results with state-of-the-art methods. Multi-focus image fusion Transformers Knowledge distillation CNNs Luo, Xiaoliu verfasserin (orcid)0000-0002-2365-4950 aut Zhang, Taiping verfasserin (orcid)0000-0001-9891-4203 aut Enthalten in Expert systems with applications Amsterdam [u.a.] : Elsevier Science, 1990 235 Online-Ressource (DE-627)320577961 (DE-600)2017237-0 (DE-576)11481807X nnns volume:235 GBV_USEFLAG_U GBV_ELV SYSFLAG_U GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_187 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2007 GBV_ILN_2008 GBV_ILN_2009 GBV_ILN_2010 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2026 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2055 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2088 GBV_ILN_2106 GBV_ILN_2110 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_2470 GBV_ILN_2507 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4242 GBV_ILN_4249 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4338 GBV_ILN_4393 GBV_ILN_4700 54.72 Künstliche Intelligenz VZ AR 235 |
allfieldsSound |
10.1016/j.eswa.2023.121156 doi (DE-627)ELV065244761 (ELSEVIER)S0957-4174(23)01658-5 DE-627 ger DE-627 rda eng 004 VZ 54.72 bkl Duan, Zhao verfasserin (orcid)0000-0001-6783-7727 aut Combining transformers with CNN for multi-focus image fusion 2023 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Recently, deep convolutional neural network (CNN) based methods for multi-focus image fusion have achieved adequate performance. However, most of them cannot obtain spatially continuous results, especially in smooth regions and edges between focused and defocused regions. In this paper, we propose a novel end-to-end method, which merits both Transformers and CNNs, as a strong alternative for multi-focus image fusion task. Transformer has advantages over a CNN in that it can extract global features. It is able to make the fusion results to be spatially consistent. The proposed architecture consists of CNN and transformer branches, where transformer branches take feature map patches as inputs and leverages the transformer to propagate global contexts among patches. Moreover, in order to improve feature representation, we introduce online knowledge distillation learning strategy (KDL). The strategy achieves better interactions between global features and local features. Specifically, we design hard target and soft target by simply yet effectively ensembling outputs of two branches, which are used to supervise CNN and transformer branches. The experiments demonstrate the superiority of our proposed architecture and achieve competitive results with state-of-the-art methods. Multi-focus image fusion Transformers Knowledge distillation CNNs Luo, Xiaoliu verfasserin (orcid)0000-0002-2365-4950 aut Zhang, Taiping verfasserin (orcid)0000-0001-9891-4203 aut Enthalten in Expert systems with applications Amsterdam [u.a.] : Elsevier Science, 1990 235 Online-Ressource (DE-627)320577961 (DE-600)2017237-0 (DE-576)11481807X nnns volume:235 GBV_USEFLAG_U GBV_ELV SYSFLAG_U GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_187 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2007 GBV_ILN_2008 GBV_ILN_2009 GBV_ILN_2010 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2026 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2055 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2088 GBV_ILN_2106 GBV_ILN_2110 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_2470 GBV_ILN_2507 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4242 GBV_ILN_4249 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4338 GBV_ILN_4393 GBV_ILN_4700 54.72 Künstliche Intelligenz VZ AR 235 |
language |
English |
source |
Enthalten in Expert systems with applications 235 volume:235 |
sourceStr |
Enthalten in Expert systems with applications 235 volume:235 |
format_phy_str_mv |
Article |
bklname |
Künstliche Intelligenz |
institution |
findex.gbv.de |
topic_facet |
Multi-focus image fusion Transformers Knowledge distillation CNNs |
dewey-raw |
004 |
isfreeaccess_bool |
false |
container_title |
Expert systems with applications |
authorswithroles_txt_mv |
Duan, Zhao @@aut@@ Luo, Xiaoliu @@aut@@ Zhang, Taiping @@aut@@ |
publishDateDaySort_date |
2023-01-01T00:00:00Z |
hierarchy_top_id |
320577961 |
dewey-sort |
14 |
id |
ELV065244761 |
language_de |
englisch |
fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV065244761</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20231205153529.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">231023s2023 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.eswa.2023.121156</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV065244761</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0957-4174(23)01658-5</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">54.72</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Duan, Zhao</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0001-6783-7727</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Combining transformers with CNN for multi-focus image fusion</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Recently, deep convolutional neural network (CNN) based methods for multi-focus image fusion have achieved adequate performance. However, most of them cannot obtain spatially continuous results, especially in smooth regions and edges between focused and defocused regions. In this paper, we propose a novel end-to-end method, which merits both Transformers and CNNs, as a strong alternative for multi-focus image fusion task. Transformer has advantages over a CNN in that it can extract global features. It is able to make the fusion results to be spatially consistent. The proposed architecture consists of CNN and transformer branches, where transformer branches take feature map patches as inputs and leverages the transformer to propagate global contexts among patches. Moreover, in order to improve feature representation, we introduce online knowledge distillation learning strategy (KDL). The strategy achieves better interactions between global features and local features. Specifically, we design hard target and soft target by simply yet effectively ensembling outputs of two branches, which are used to supervise CNN and transformer branches. The experiments demonstrate the superiority of our proposed architecture and achieve competitive results with state-of-the-art methods.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Multi-focus image fusion</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Transformers</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Knowledge distillation</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">CNNs</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Luo, Xiaoliu</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0002-2365-4950</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhang, Taiping</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0001-9891-4203</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Expert systems with applications</subfield><subfield code="d">Amsterdam [u.a.] : Elsevier Science, 1990</subfield><subfield code="g">235</subfield><subfield code="h">Online-Ressource</subfield><subfield code="w">(DE-627)320577961</subfield><subfield code="w">(DE-600)2017237-0</subfield><subfield code="w">(DE-576)11481807X</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:235</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_32</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_74</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_90</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_100</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_101</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_150</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_187</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_224</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_702</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2001</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2003</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2004</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2005</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2007</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2008</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2009</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2010</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2011</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2015</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2020</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2021</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2025</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2026</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2027</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2034</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2044</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2048</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2049</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2050</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2055</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2056</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2059</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2061</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2064</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2088</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2106</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2111</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2122</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2129</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2143</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2152</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2153</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2190</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2232</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2336</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2470</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2507</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4035</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4242</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4251</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4326</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4333</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4334</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4393</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">54.72</subfield><subfield code="j">Künstliche Intelligenz</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">235</subfield></datafield></record></collection>
|
author |
Duan, Zhao |
spellingShingle |
Duan, Zhao ddc 004 bkl 54.72 misc Multi-focus image fusion misc Transformers misc Knowledge distillation misc CNNs Combining transformers with CNN for multi-focus image fusion |
authorStr |
Duan, Zhao |
ppnlink_with_tag_str_mv |
@@773@@(DE-627)320577961 |
format |
electronic Article |
dewey-ones |
004 - Data processing & computer science |
delete_txt_mv |
keep |
author_role |
aut aut aut |
collection |
elsevier |
remote_str |
true |
illustrated |
Not Illustrated |
topic_title |
004 VZ 54.72 bkl Combining transformers with CNN for multi-focus image fusion Multi-focus image fusion Transformers Knowledge distillation CNNs |
topic |
ddc 004 bkl 54.72 misc Multi-focus image fusion misc Transformers misc Knowledge distillation misc CNNs |
topic_unstemmed |
ddc 004 bkl 54.72 misc Multi-focus image fusion misc Transformers misc Knowledge distillation misc CNNs |
topic_browse |
ddc 004 bkl 54.72 misc Multi-focus image fusion misc Transformers misc Knowledge distillation misc CNNs |
format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
format_main_str_mv |
Text Zeitschrift/Artikel |
carriertype_str_mv |
cr |
hierarchy_parent_title |
Expert systems with applications |
hierarchy_parent_id |
320577961 |
dewey-tens |
000 - Computer science, knowledge & systems |
hierarchy_top_title |
Expert systems with applications |
isfreeaccess_txt |
false |
familylinks_str_mv |
(DE-627)320577961 (DE-600)2017237-0 (DE-576)11481807X |
title |
Combining transformers with CNN for multi-focus image fusion |
ctrlnum |
(DE-627)ELV065244761 (ELSEVIER)S0957-4174(23)01658-5 |
title_full |
Combining transformers with CNN for multi-focus image fusion |
author_sort |
Duan, Zhao |
journal |
Expert systems with applications |
journalStr |
Expert systems with applications |
lang_code |
eng |
isOA_bool |
false |
dewey-hundreds |
000 - Computer science, information & general works |
recordtype |
marc |
publishDateSort |
2023 |
contenttype_str_mv |
zzz |
author_browse |
Duan, Zhao Luo, Xiaoliu Zhang, Taiping |
container_volume |
235 |
class |
004 VZ 54.72 bkl |
format_se |
Elektronische Aufsätze |
author-letter |
Duan, Zhao |
doi_str_mv |
10.1016/j.eswa.2023.121156 |
normlink |
(ORCID)0000-0001-6783-7727 (ORCID)0000-0002-2365-4950 (ORCID)0000-0001-9891-4203 |
normlink_prefix_str_mv |
(orcid)0000-0001-6783-7727 (orcid)0000-0002-2365-4950 (orcid)0000-0001-9891-4203 |
dewey-full |
004 |
author2-role |
verfasserin |
title_sort |
combining transformers with cnn for multi-focus image fusion |
title_auth |
Combining transformers with CNN for multi-focus image fusion |
abstract |
Recently, deep convolutional neural network (CNN) based methods for multi-focus image fusion have achieved adequate performance. However, most of them cannot obtain spatially continuous results, especially in smooth regions and edges between focused and defocused regions. In this paper, we propose a novel end-to-end method, which merits both Transformers and CNNs, as a strong alternative for multi-focus image fusion task. Transformer has advantages over a CNN in that it can extract global features. It is able to make the fusion results to be spatially consistent. The proposed architecture consists of CNN and transformer branches, where transformer branches take feature map patches as inputs and leverages the transformer to propagate global contexts among patches. Moreover, in order to improve feature representation, we introduce online knowledge distillation learning strategy (KDL). The strategy achieves better interactions between global features and local features. Specifically, we design hard target and soft target by simply yet effectively ensembling outputs of two branches, which are used to supervise CNN and transformer branches. The experiments demonstrate the superiority of our proposed architecture and achieve competitive results with state-of-the-art methods. |
abstractGer |
Recently, deep convolutional neural network (CNN) based methods for multi-focus image fusion have achieved adequate performance. However, most of them cannot obtain spatially continuous results, especially in smooth regions and edges between focused and defocused regions. In this paper, we propose a novel end-to-end method, which merits both Transformers and CNNs, as a strong alternative for multi-focus image fusion task. Transformer has advantages over a CNN in that it can extract global features. It is able to make the fusion results to be spatially consistent. The proposed architecture consists of CNN and transformer branches, where transformer branches take feature map patches as inputs and leverages the transformer to propagate global contexts among patches. Moreover, in order to improve feature representation, we introduce online knowledge distillation learning strategy (KDL). The strategy achieves better interactions between global features and local features. Specifically, we design hard target and soft target by simply yet effectively ensembling outputs of two branches, which are used to supervise CNN and transformer branches. The experiments demonstrate the superiority of our proposed architecture and achieve competitive results with state-of-the-art methods. |
abstract_unstemmed |
Recently, deep convolutional neural network (CNN) based methods for multi-focus image fusion have achieved adequate performance. However, most of them cannot obtain spatially continuous results, especially in smooth regions and edges between focused and defocused regions. In this paper, we propose a novel end-to-end method, which merits both Transformers and CNNs, as a strong alternative for multi-focus image fusion task. Transformer has advantages over a CNN in that it can extract global features. It is able to make the fusion results to be spatially consistent. The proposed architecture consists of CNN and transformer branches, where transformer branches take feature map patches as inputs and leverages the transformer to propagate global contexts among patches. Moreover, in order to improve feature representation, we introduce online knowledge distillation learning strategy (KDL). The strategy achieves better interactions between global features and local features. Specifically, we design hard target and soft target by simply yet effectively ensembling outputs of two branches, which are used to supervise CNN and transformer branches. The experiments demonstrate the superiority of our proposed architecture and achieve competitive results with state-of-the-art methods. |
collection_details |
GBV_USEFLAG_U GBV_ELV SYSFLAG_U GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_187 GBV_ILN_213 GBV_ILN_224 GBV_ILN_230 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2007 GBV_ILN_2008 GBV_ILN_2009 GBV_ILN_2010 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2026 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2055 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2088 GBV_ILN_2106 GBV_ILN_2110 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2232 GBV_ILN_2336 GBV_ILN_2470 GBV_ILN_2507 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4242 GBV_ILN_4249 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4338 GBV_ILN_4393 GBV_ILN_4700 |
title_short |
Combining transformers with CNN for multi-focus image fusion |
remote_bool |
true |
author2 |
Luo, Xiaoliu Zhang, Taiping |
author2Str |
Luo, Xiaoliu Zhang, Taiping |
ppnlink |
320577961 |
mediatype_str_mv |
c |
isOA_txt |
false |
hochschulschrift_bool |
false |
doi_str |
10.1016/j.eswa.2023.121156 |
up_date |
2024-07-06T22:21:05.228Z |
_version_ |
1803869974933012480 |
fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV065244761</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20231205153529.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">231023s2023 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.eswa.2023.121156</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV065244761</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0957-4174(23)01658-5</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">54.72</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Duan, Zhao</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0001-6783-7727</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Combining transformers with CNN for multi-focus image fusion</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Recently, deep convolutional neural network (CNN) based methods for multi-focus image fusion have achieved adequate performance. However, most of them cannot obtain spatially continuous results, especially in smooth regions and edges between focused and defocused regions. In this paper, we propose a novel end-to-end method, which merits both Transformers and CNNs, as a strong alternative for multi-focus image fusion task. Transformer has advantages over a CNN in that it can extract global features. It is able to make the fusion results to be spatially consistent. The proposed architecture consists of CNN and transformer branches, where transformer branches take feature map patches as inputs and leverages the transformer to propagate global contexts among patches. Moreover, in order to improve feature representation, we introduce online knowledge distillation learning strategy (KDL). The strategy achieves better interactions between global features and local features. Specifically, we design hard target and soft target by simply yet effectively ensembling outputs of two branches, which are used to supervise CNN and transformer branches. The experiments demonstrate the superiority of our proposed architecture and achieve competitive results with state-of-the-art methods.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Multi-focus image fusion</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Transformers</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Knowledge distillation</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">CNNs</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Luo, Xiaoliu</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0002-2365-4950</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhang, Taiping</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0001-9891-4203</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Expert systems with applications</subfield><subfield code="d">Amsterdam [u.a.] : Elsevier Science, 1990</subfield><subfield code="g">235</subfield><subfield code="h">Online-Ressource</subfield><subfield code="w">(DE-627)320577961</subfield><subfield code="w">(DE-600)2017237-0</subfield><subfield code="w">(DE-576)11481807X</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:235</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_32</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_74</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_90</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_100</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_101</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_150</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_187</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_224</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_702</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2001</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2003</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2004</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2005</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2007</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2008</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2009</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2010</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2011</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2015</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2020</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2021</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2025</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2026</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2027</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2034</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2044</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2048</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2049</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2050</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2055</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2056</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2059</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2061</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2064</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2088</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2106</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2111</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2122</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2129</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2143</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2152</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2153</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2190</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2232</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2336</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2470</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2507</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4035</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4242</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4251</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4326</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4333</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4334</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4393</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">54.72</subfield><subfield code="j">Künstliche Intelligenz</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">235</subfield></datafield></record></collection>
|
score |
7.400194 |