Single-Shot Detection Based on Cyclic Attention
The shallow feature map of the single-shot detector (SSD) is not always conducive to enhancing the recognition precision for a small object because of the lack of contextual information. In this research, a single-shot detection algorithm based on cyclic attention (CA-SSD) is proposed to construct a...
Ausführliche Beschreibung
Autor*in: |
Kebai Hu [verfasserIn] Daochun Xu [verfasserIn] Jiangming Kan [verfasserIn] |
---|
Format: |
E-Artikel |
---|---|
Sprache: |
Englisch |
Erschienen: |
2021 |
---|
Schlagwörter: |
---|
Übergeordnetes Werk: |
In: IEEE Access - IEEE, 2014, 9(2021), Seite 50557-50569 |
---|---|
Übergeordnetes Werk: |
volume:9 ; year:2021 ; pages:50557-50569 |
Links: |
---|
DOI / URN: |
10.1109/ACCESS.2021.3068533 |
---|
Katalog-ID: |
DOAJ007989261 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | DOAJ007989261 | ||
003 | DE-627 | ||
005 | 20230310002656.0 | ||
007 | cr uuu---uuuuu | ||
008 | 230225s2021 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1109/ACCESS.2021.3068533 |2 doi | |
035 | |a (DE-627)DOAJ007989261 | ||
035 | |a (DE-599)DOAJ2bd8160d5d6c4234903386cce70f4c21 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
050 | 0 | |a TK1-9971 | |
100 | 0 | |a Kebai Hu |e verfasserin |4 aut | |
245 | 1 | 0 | |a Single-Shot Detection Based on Cyclic Attention |
264 | 1 | |c 2021 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a Computermedien |b c |2 rdamedia | ||
338 | |a Online-Ressource |b cr |2 rdacarrier | ||
520 | |a The shallow feature map of the single-shot detector (SSD) is not always conducive to enhancing the recognition precision for a small object because of the lack of contextual information. In this research, a single-shot detection algorithm based on cyclic attention (CA-SSD) is proposed to construct a fast and accurate detector that efficiently obtains full-image contextual information. Our network is constructed by integrating ResNet-34 and proposed novel cyclic attention blocks. This type of building block aggregates different transformations, one of which includes an attention module that uses a long but narrow pooling kernel to acquire horizontal and vertical contextual information for each pixel of all pixels. Each pixel eventually captures the full-image dependencies by following an even further cyclic operation. Our design considers the variability of the gradient, which not only improves the reliability of the cyclic attention block but also cuts the number of parameters for computation. Additionally, by exploring the effects of the stem block and its stride on the performance of ResNet-based SSD algorithms, our network retains more detailed information. For an input size of 300 <inline-formula< <tex-math notation="LaTeX"<$\times $ </tex-math<</inline-formula< 300, CA-SSD attained 82.5% mAP on PASCAL VOC 2007 test, 78.4% mAP on PASCAL VOC 2012 test, and 32.7% mAP on MS COCO. Experimental results achieved with CA-SSD surpass the best results achieved with the traditional SSD and other advanced object detection algorithms while real-time speed is maintained. | ||
650 | 4 | |a Object detection | |
650 | 4 | |a single-shot detector | |
650 | 4 | |a ResNet | |
650 | 4 | |a cyclic attention | |
653 | 0 | |a Electrical engineering. Electronics. Nuclear engineering | |
700 | 0 | |a Daochun Xu |e verfasserin |4 aut | |
700 | 0 | |a Jiangming Kan |e verfasserin |4 aut | |
773 | 0 | 8 | |i In |t IEEE Access |d IEEE, 2014 |g 9(2021), Seite 50557-50569 |w (DE-627)728440385 |w (DE-600)2687964-5 |x 21693536 |7 nnns |
773 | 1 | 8 | |g volume:9 |g year:2021 |g pages:50557-50569 |
856 | 4 | 0 | |u https://doi.org/10.1109/ACCESS.2021.3068533 |z kostenfrei |
856 | 4 | 0 | |u https://doaj.org/article/2bd8160d5d6c4234903386cce70f4c21 |z kostenfrei |
856 | 4 | 0 | |u https://ieeexplore.ieee.org/document/9385111/ |z kostenfrei |
856 | 4 | 2 | |u https://doaj.org/toc/2169-3536 |y Journal toc |z kostenfrei |
912 | |a GBV_USEFLAG_A | ||
912 | |a SYSFLAG_A | ||
912 | |a GBV_DOAJ | ||
912 | |a GBV_ILN_11 | ||
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_39 | ||
912 | |a GBV_ILN_40 | ||
912 | |a GBV_ILN_60 | ||
912 | |a GBV_ILN_62 | ||
912 | |a GBV_ILN_63 | ||
912 | |a GBV_ILN_65 | ||
912 | |a GBV_ILN_69 | ||
912 | |a GBV_ILN_70 | ||
912 | |a GBV_ILN_73 | ||
912 | |a GBV_ILN_95 | ||
912 | |a GBV_ILN_105 | ||
912 | |a GBV_ILN_110 | ||
912 | |a GBV_ILN_151 | ||
912 | |a GBV_ILN_161 | ||
912 | |a GBV_ILN_170 | ||
912 | |a GBV_ILN_213 | ||
912 | |a GBV_ILN_230 | ||
912 | |a GBV_ILN_285 | ||
912 | |a GBV_ILN_293 | ||
912 | |a GBV_ILN_370 | ||
912 | |a GBV_ILN_602 | ||
912 | |a GBV_ILN_2014 | ||
912 | |a GBV_ILN_4012 | ||
912 | |a GBV_ILN_4037 | ||
912 | |a GBV_ILN_4112 | ||
912 | |a GBV_ILN_4125 | ||
912 | |a GBV_ILN_4126 | ||
912 | |a GBV_ILN_4249 | ||
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_4335 | ||
912 | |a GBV_ILN_4338 | ||
912 | |a GBV_ILN_4367 | ||
912 | |a GBV_ILN_4700 | ||
951 | |a AR | ||
952 | |d 9 |j 2021 |h 50557-50569 |
author_variant |
k h kh d x dx j k jk |
---|---|
matchkey_str |
article:21693536:2021----::igehteetobsdnyl |
hierarchy_sort_str |
2021 |
callnumber-subject-code |
TK |
publishDate |
2021 |
allfields |
10.1109/ACCESS.2021.3068533 doi (DE-627)DOAJ007989261 (DE-599)DOAJ2bd8160d5d6c4234903386cce70f4c21 DE-627 ger DE-627 rakwb eng TK1-9971 Kebai Hu verfasserin aut Single-Shot Detection Based on Cyclic Attention 2021 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier The shallow feature map of the single-shot detector (SSD) is not always conducive to enhancing the recognition precision for a small object because of the lack of contextual information. In this research, a single-shot detection algorithm based on cyclic attention (CA-SSD) is proposed to construct a fast and accurate detector that efficiently obtains full-image contextual information. Our network is constructed by integrating ResNet-34 and proposed novel cyclic attention blocks. This type of building block aggregates different transformations, one of which includes an attention module that uses a long but narrow pooling kernel to acquire horizontal and vertical contextual information for each pixel of all pixels. Each pixel eventually captures the full-image dependencies by following an even further cyclic operation. Our design considers the variability of the gradient, which not only improves the reliability of the cyclic attention block but also cuts the number of parameters for computation. Additionally, by exploring the effects of the stem block and its stride on the performance of ResNet-based SSD algorithms, our network retains more detailed information. For an input size of 300 <inline-formula< <tex-math notation="LaTeX"<$\times $ </tex-math<</inline-formula< 300, CA-SSD attained 82.5% mAP on PASCAL VOC 2007 test, 78.4% mAP on PASCAL VOC 2012 test, and 32.7% mAP on MS COCO. Experimental results achieved with CA-SSD surpass the best results achieved with the traditional SSD and other advanced object detection algorithms while real-time speed is maintained. Object detection single-shot detector ResNet cyclic attention Electrical engineering. Electronics. Nuclear engineering Daochun Xu verfasserin aut Jiangming Kan verfasserin aut In IEEE Access IEEE, 2014 9(2021), Seite 50557-50569 (DE-627)728440385 (DE-600)2687964-5 21693536 nnns volume:9 year:2021 pages:50557-50569 https://doi.org/10.1109/ACCESS.2021.3068533 kostenfrei https://doaj.org/article/2bd8160d5d6c4234903386cce70f4c21 kostenfrei https://ieeexplore.ieee.org/document/9385111/ kostenfrei https://doaj.org/toc/2169-3536 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 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_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 9 2021 50557-50569 |
spelling |
10.1109/ACCESS.2021.3068533 doi (DE-627)DOAJ007989261 (DE-599)DOAJ2bd8160d5d6c4234903386cce70f4c21 DE-627 ger DE-627 rakwb eng TK1-9971 Kebai Hu verfasserin aut Single-Shot Detection Based on Cyclic Attention 2021 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier The shallow feature map of the single-shot detector (SSD) is not always conducive to enhancing the recognition precision for a small object because of the lack of contextual information. In this research, a single-shot detection algorithm based on cyclic attention (CA-SSD) is proposed to construct a fast and accurate detector that efficiently obtains full-image contextual information. Our network is constructed by integrating ResNet-34 and proposed novel cyclic attention blocks. This type of building block aggregates different transformations, one of which includes an attention module that uses a long but narrow pooling kernel to acquire horizontal and vertical contextual information for each pixel of all pixels. Each pixel eventually captures the full-image dependencies by following an even further cyclic operation. Our design considers the variability of the gradient, which not only improves the reliability of the cyclic attention block but also cuts the number of parameters for computation. Additionally, by exploring the effects of the stem block and its stride on the performance of ResNet-based SSD algorithms, our network retains more detailed information. For an input size of 300 <inline-formula< <tex-math notation="LaTeX"<$\times $ </tex-math<</inline-formula< 300, CA-SSD attained 82.5% mAP on PASCAL VOC 2007 test, 78.4% mAP on PASCAL VOC 2012 test, and 32.7% mAP on MS COCO. Experimental results achieved with CA-SSD surpass the best results achieved with the traditional SSD and other advanced object detection algorithms while real-time speed is maintained. Object detection single-shot detector ResNet cyclic attention Electrical engineering. Electronics. Nuclear engineering Daochun Xu verfasserin aut Jiangming Kan verfasserin aut In IEEE Access IEEE, 2014 9(2021), Seite 50557-50569 (DE-627)728440385 (DE-600)2687964-5 21693536 nnns volume:9 year:2021 pages:50557-50569 https://doi.org/10.1109/ACCESS.2021.3068533 kostenfrei https://doaj.org/article/2bd8160d5d6c4234903386cce70f4c21 kostenfrei https://ieeexplore.ieee.org/document/9385111/ kostenfrei https://doaj.org/toc/2169-3536 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 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_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 9 2021 50557-50569 |
allfields_unstemmed |
10.1109/ACCESS.2021.3068533 doi (DE-627)DOAJ007989261 (DE-599)DOAJ2bd8160d5d6c4234903386cce70f4c21 DE-627 ger DE-627 rakwb eng TK1-9971 Kebai Hu verfasserin aut Single-Shot Detection Based on Cyclic Attention 2021 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier The shallow feature map of the single-shot detector (SSD) is not always conducive to enhancing the recognition precision for a small object because of the lack of contextual information. In this research, a single-shot detection algorithm based on cyclic attention (CA-SSD) is proposed to construct a fast and accurate detector that efficiently obtains full-image contextual information. Our network is constructed by integrating ResNet-34 and proposed novel cyclic attention blocks. This type of building block aggregates different transformations, one of which includes an attention module that uses a long but narrow pooling kernel to acquire horizontal and vertical contextual information for each pixel of all pixels. Each pixel eventually captures the full-image dependencies by following an even further cyclic operation. Our design considers the variability of the gradient, which not only improves the reliability of the cyclic attention block but also cuts the number of parameters for computation. Additionally, by exploring the effects of the stem block and its stride on the performance of ResNet-based SSD algorithms, our network retains more detailed information. For an input size of 300 <inline-formula< <tex-math notation="LaTeX"<$\times $ </tex-math<</inline-formula< 300, CA-SSD attained 82.5% mAP on PASCAL VOC 2007 test, 78.4% mAP on PASCAL VOC 2012 test, and 32.7% mAP on MS COCO. Experimental results achieved with CA-SSD surpass the best results achieved with the traditional SSD and other advanced object detection algorithms while real-time speed is maintained. Object detection single-shot detector ResNet cyclic attention Electrical engineering. Electronics. Nuclear engineering Daochun Xu verfasserin aut Jiangming Kan verfasserin aut In IEEE Access IEEE, 2014 9(2021), Seite 50557-50569 (DE-627)728440385 (DE-600)2687964-5 21693536 nnns volume:9 year:2021 pages:50557-50569 https://doi.org/10.1109/ACCESS.2021.3068533 kostenfrei https://doaj.org/article/2bd8160d5d6c4234903386cce70f4c21 kostenfrei https://ieeexplore.ieee.org/document/9385111/ kostenfrei https://doaj.org/toc/2169-3536 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 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_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 9 2021 50557-50569 |
allfieldsGer |
10.1109/ACCESS.2021.3068533 doi (DE-627)DOAJ007989261 (DE-599)DOAJ2bd8160d5d6c4234903386cce70f4c21 DE-627 ger DE-627 rakwb eng TK1-9971 Kebai Hu verfasserin aut Single-Shot Detection Based on Cyclic Attention 2021 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier The shallow feature map of the single-shot detector (SSD) is not always conducive to enhancing the recognition precision for a small object because of the lack of contextual information. In this research, a single-shot detection algorithm based on cyclic attention (CA-SSD) is proposed to construct a fast and accurate detector that efficiently obtains full-image contextual information. Our network is constructed by integrating ResNet-34 and proposed novel cyclic attention blocks. This type of building block aggregates different transformations, one of which includes an attention module that uses a long but narrow pooling kernel to acquire horizontal and vertical contextual information for each pixel of all pixels. Each pixel eventually captures the full-image dependencies by following an even further cyclic operation. Our design considers the variability of the gradient, which not only improves the reliability of the cyclic attention block but also cuts the number of parameters for computation. Additionally, by exploring the effects of the stem block and its stride on the performance of ResNet-based SSD algorithms, our network retains more detailed information. For an input size of 300 <inline-formula< <tex-math notation="LaTeX"<$\times $ </tex-math<</inline-formula< 300, CA-SSD attained 82.5% mAP on PASCAL VOC 2007 test, 78.4% mAP on PASCAL VOC 2012 test, and 32.7% mAP on MS COCO. Experimental results achieved with CA-SSD surpass the best results achieved with the traditional SSD and other advanced object detection algorithms while real-time speed is maintained. Object detection single-shot detector ResNet cyclic attention Electrical engineering. Electronics. Nuclear engineering Daochun Xu verfasserin aut Jiangming Kan verfasserin aut In IEEE Access IEEE, 2014 9(2021), Seite 50557-50569 (DE-627)728440385 (DE-600)2687964-5 21693536 nnns volume:9 year:2021 pages:50557-50569 https://doi.org/10.1109/ACCESS.2021.3068533 kostenfrei https://doaj.org/article/2bd8160d5d6c4234903386cce70f4c21 kostenfrei https://ieeexplore.ieee.org/document/9385111/ kostenfrei https://doaj.org/toc/2169-3536 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 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_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 9 2021 50557-50569 |
allfieldsSound |
10.1109/ACCESS.2021.3068533 doi (DE-627)DOAJ007989261 (DE-599)DOAJ2bd8160d5d6c4234903386cce70f4c21 DE-627 ger DE-627 rakwb eng TK1-9971 Kebai Hu verfasserin aut Single-Shot Detection Based on Cyclic Attention 2021 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier The shallow feature map of the single-shot detector (SSD) is not always conducive to enhancing the recognition precision for a small object because of the lack of contextual information. In this research, a single-shot detection algorithm based on cyclic attention (CA-SSD) is proposed to construct a fast and accurate detector that efficiently obtains full-image contextual information. Our network is constructed by integrating ResNet-34 and proposed novel cyclic attention blocks. This type of building block aggregates different transformations, one of which includes an attention module that uses a long but narrow pooling kernel to acquire horizontal and vertical contextual information for each pixel of all pixels. Each pixel eventually captures the full-image dependencies by following an even further cyclic operation. Our design considers the variability of the gradient, which not only improves the reliability of the cyclic attention block but also cuts the number of parameters for computation. Additionally, by exploring the effects of the stem block and its stride on the performance of ResNet-based SSD algorithms, our network retains more detailed information. For an input size of 300 <inline-formula< <tex-math notation="LaTeX"<$\times $ </tex-math<</inline-formula< 300, CA-SSD attained 82.5% mAP on PASCAL VOC 2007 test, 78.4% mAP on PASCAL VOC 2012 test, and 32.7% mAP on MS COCO. Experimental results achieved with CA-SSD surpass the best results achieved with the traditional SSD and other advanced object detection algorithms while real-time speed is maintained. Object detection single-shot detector ResNet cyclic attention Electrical engineering. Electronics. Nuclear engineering Daochun Xu verfasserin aut Jiangming Kan verfasserin aut In IEEE Access IEEE, 2014 9(2021), Seite 50557-50569 (DE-627)728440385 (DE-600)2687964-5 21693536 nnns volume:9 year:2021 pages:50557-50569 https://doi.org/10.1109/ACCESS.2021.3068533 kostenfrei https://doaj.org/article/2bd8160d5d6c4234903386cce70f4c21 kostenfrei https://ieeexplore.ieee.org/document/9385111/ kostenfrei https://doaj.org/toc/2169-3536 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 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_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 9 2021 50557-50569 |
language |
English |
source |
In IEEE Access 9(2021), Seite 50557-50569 volume:9 year:2021 pages:50557-50569 |
sourceStr |
In IEEE Access 9(2021), Seite 50557-50569 volume:9 year:2021 pages:50557-50569 |
format_phy_str_mv |
Article |
institution |
findex.gbv.de |
topic_facet |
Object detection single-shot detector ResNet cyclic attention Electrical engineering. Electronics. Nuclear engineering |
isfreeaccess_bool |
true |
container_title |
IEEE Access |
authorswithroles_txt_mv |
Kebai Hu @@aut@@ Daochun Xu @@aut@@ Jiangming Kan @@aut@@ |
publishDateDaySort_date |
2021-01-01T00:00:00Z |
hierarchy_top_id |
728440385 |
id |
DOAJ007989261 |
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">DOAJ007989261</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230310002656.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230225s2021 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1109/ACCESS.2021.3068533</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ007989261</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ2bd8160d5d6c4234903386cce70f4c21</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">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">TK1-9971</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Kebai Hu</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Single-Shot Detection Based on Cyclic Attention</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2021</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</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">The shallow feature map of the single-shot detector (SSD) is not always conducive to enhancing the recognition precision for a small object because of the lack of contextual information. In this research, a single-shot detection algorithm based on cyclic attention (CA-SSD) is proposed to construct a fast and accurate detector that efficiently obtains full-image contextual information. Our network is constructed by integrating ResNet-34 and proposed novel cyclic attention blocks. This type of building block aggregates different transformations, one of which includes an attention module that uses a long but narrow pooling kernel to acquire horizontal and vertical contextual information for each pixel of all pixels. Each pixel eventually captures the full-image dependencies by following an even further cyclic operation. Our design considers the variability of the gradient, which not only improves the reliability of the cyclic attention block but also cuts the number of parameters for computation. Additionally, by exploring the effects of the stem block and its stride on the performance of ResNet-based SSD algorithms, our network retains more detailed information. For an input size of 300 <inline-formula< <tex-math notation="LaTeX"<$\times $ </tex-math<</inline-formula< 300, CA-SSD attained 82.5% mAP on PASCAL VOC 2007 test, 78.4% mAP on PASCAL VOC 2012 test, and 32.7% mAP on MS COCO. Experimental results achieved with CA-SSD surpass the best results achieved with the traditional SSD and other advanced object detection algorithms while real-time speed is maintained.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Object detection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">single-shot detector</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">ResNet</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">cyclic attention</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Electrical engineering. Electronics. Nuclear engineering</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Daochun Xu</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Jiangming Kan</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">IEEE Access</subfield><subfield code="d">IEEE, 2014</subfield><subfield code="g">9(2021), Seite 50557-50569</subfield><subfield code="w">(DE-627)728440385</subfield><subfield code="w">(DE-600)2687964-5</subfield><subfield code="x">21693536</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:9</subfield><subfield code="g">year:2021</subfield><subfield code="g">pages:50557-50569</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1109/ACCESS.2021.3068533</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/2bd8160d5d6c4234903386cce70f4c21</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://ieeexplore.ieee.org/document/9385111/</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2169-3536</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</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_39</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_63</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_95</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_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</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_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</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_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</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_4126</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_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_4335</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_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">9</subfield><subfield code="j">2021</subfield><subfield code="h">50557-50569</subfield></datafield></record></collection>
|
callnumber-first |
T - Technology |
author |
Kebai Hu |
spellingShingle |
Kebai Hu misc TK1-9971 misc Object detection misc single-shot detector misc ResNet misc cyclic attention misc Electrical engineering. Electronics. Nuclear engineering Single-Shot Detection Based on Cyclic Attention |
authorStr |
Kebai Hu |
ppnlink_with_tag_str_mv |
@@773@@(DE-627)728440385 |
format |
electronic Article |
delete_txt_mv |
keep |
author_role |
aut aut aut |
collection |
DOAJ |
remote_str |
true |
callnumber-label |
TK1-9971 |
illustrated |
Not Illustrated |
issn |
21693536 |
topic_title |
TK1-9971 Single-Shot Detection Based on Cyclic Attention Object detection single-shot detector ResNet cyclic attention |
topic |
misc TK1-9971 misc Object detection misc single-shot detector misc ResNet misc cyclic attention misc Electrical engineering. Electronics. Nuclear engineering |
topic_unstemmed |
misc TK1-9971 misc Object detection misc single-shot detector misc ResNet misc cyclic attention misc Electrical engineering. Electronics. Nuclear engineering |
topic_browse |
misc TK1-9971 misc Object detection misc single-shot detector misc ResNet misc cyclic attention misc Electrical engineering. Electronics. Nuclear engineering |
format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
format_main_str_mv |
Text Zeitschrift/Artikel |
carriertype_str_mv |
cr |
hierarchy_parent_title |
IEEE Access |
hierarchy_parent_id |
728440385 |
hierarchy_top_title |
IEEE Access |
isfreeaccess_txt |
true |
familylinks_str_mv |
(DE-627)728440385 (DE-600)2687964-5 |
title |
Single-Shot Detection Based on Cyclic Attention |
ctrlnum |
(DE-627)DOAJ007989261 (DE-599)DOAJ2bd8160d5d6c4234903386cce70f4c21 |
title_full |
Single-Shot Detection Based on Cyclic Attention |
author_sort |
Kebai Hu |
journal |
IEEE Access |
journalStr |
IEEE Access |
callnumber-first-code |
T |
lang_code |
eng |
isOA_bool |
true |
recordtype |
marc |
publishDateSort |
2021 |
contenttype_str_mv |
txt |
container_start_page |
50557 |
author_browse |
Kebai Hu Daochun Xu Jiangming Kan |
container_volume |
9 |
class |
TK1-9971 |
format_se |
Elektronische Aufsätze |
author-letter |
Kebai Hu |
doi_str_mv |
10.1109/ACCESS.2021.3068533 |
author2-role |
verfasserin |
title_sort |
single-shot detection based on cyclic attention |
callnumber |
TK1-9971 |
title_auth |
Single-Shot Detection Based on Cyclic Attention |
abstract |
The shallow feature map of the single-shot detector (SSD) is not always conducive to enhancing the recognition precision for a small object because of the lack of contextual information. In this research, a single-shot detection algorithm based on cyclic attention (CA-SSD) is proposed to construct a fast and accurate detector that efficiently obtains full-image contextual information. Our network is constructed by integrating ResNet-34 and proposed novel cyclic attention blocks. This type of building block aggregates different transformations, one of which includes an attention module that uses a long but narrow pooling kernel to acquire horizontal and vertical contextual information for each pixel of all pixels. Each pixel eventually captures the full-image dependencies by following an even further cyclic operation. Our design considers the variability of the gradient, which not only improves the reliability of the cyclic attention block but also cuts the number of parameters for computation. Additionally, by exploring the effects of the stem block and its stride on the performance of ResNet-based SSD algorithms, our network retains more detailed information. For an input size of 300 <inline-formula< <tex-math notation="LaTeX"<$\times $ </tex-math<</inline-formula< 300, CA-SSD attained 82.5% mAP on PASCAL VOC 2007 test, 78.4% mAP on PASCAL VOC 2012 test, and 32.7% mAP on MS COCO. Experimental results achieved with CA-SSD surpass the best results achieved with the traditional SSD and other advanced object detection algorithms while real-time speed is maintained. |
abstractGer |
The shallow feature map of the single-shot detector (SSD) is not always conducive to enhancing the recognition precision for a small object because of the lack of contextual information. In this research, a single-shot detection algorithm based on cyclic attention (CA-SSD) is proposed to construct a fast and accurate detector that efficiently obtains full-image contextual information. Our network is constructed by integrating ResNet-34 and proposed novel cyclic attention blocks. This type of building block aggregates different transformations, one of which includes an attention module that uses a long but narrow pooling kernel to acquire horizontal and vertical contextual information for each pixel of all pixels. Each pixel eventually captures the full-image dependencies by following an even further cyclic operation. Our design considers the variability of the gradient, which not only improves the reliability of the cyclic attention block but also cuts the number of parameters for computation. Additionally, by exploring the effects of the stem block and its stride on the performance of ResNet-based SSD algorithms, our network retains more detailed information. For an input size of 300 <inline-formula< <tex-math notation="LaTeX"<$\times $ </tex-math<</inline-formula< 300, CA-SSD attained 82.5% mAP on PASCAL VOC 2007 test, 78.4% mAP on PASCAL VOC 2012 test, and 32.7% mAP on MS COCO. Experimental results achieved with CA-SSD surpass the best results achieved with the traditional SSD and other advanced object detection algorithms while real-time speed is maintained. |
abstract_unstemmed |
The shallow feature map of the single-shot detector (SSD) is not always conducive to enhancing the recognition precision for a small object because of the lack of contextual information. In this research, a single-shot detection algorithm based on cyclic attention (CA-SSD) is proposed to construct a fast and accurate detector that efficiently obtains full-image contextual information. Our network is constructed by integrating ResNet-34 and proposed novel cyclic attention blocks. This type of building block aggregates different transformations, one of which includes an attention module that uses a long but narrow pooling kernel to acquire horizontal and vertical contextual information for each pixel of all pixels. Each pixel eventually captures the full-image dependencies by following an even further cyclic operation. Our design considers the variability of the gradient, which not only improves the reliability of the cyclic attention block but also cuts the number of parameters for computation. Additionally, by exploring the effects of the stem block and its stride on the performance of ResNet-based SSD algorithms, our network retains more detailed information. For an input size of 300 <inline-formula< <tex-math notation="LaTeX"<$\times $ </tex-math<</inline-formula< 300, CA-SSD attained 82.5% mAP on PASCAL VOC 2007 test, 78.4% mAP on PASCAL VOC 2012 test, and 32.7% mAP on MS COCO. Experimental results achieved with CA-SSD surpass the best results achieved with the traditional SSD and other advanced object detection algorithms while real-time speed is maintained. |
collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 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_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 |
title_short |
Single-Shot Detection Based on Cyclic Attention |
url |
https://doi.org/10.1109/ACCESS.2021.3068533 https://doaj.org/article/2bd8160d5d6c4234903386cce70f4c21 https://ieeexplore.ieee.org/document/9385111/ https://doaj.org/toc/2169-3536 |
remote_bool |
true |
author2 |
Daochun Xu Jiangming Kan |
author2Str |
Daochun Xu Jiangming Kan |
ppnlink |
728440385 |
callnumber-subject |
TK - Electrical and Nuclear Engineering |
mediatype_str_mv |
c |
isOA_txt |
true |
hochschulschrift_bool |
false |
doi_str |
10.1109/ACCESS.2021.3068533 |
callnumber-a |
TK1-9971 |
up_date |
2024-07-03T15:19:15.570Z |
_version_ |
1803571644949594112 |
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">DOAJ007989261</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230310002656.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230225s2021 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1109/ACCESS.2021.3068533</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ007989261</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ2bd8160d5d6c4234903386cce70f4c21</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">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">TK1-9971</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Kebai Hu</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Single-Shot Detection Based on Cyclic Attention</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2021</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</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">The shallow feature map of the single-shot detector (SSD) is not always conducive to enhancing the recognition precision for a small object because of the lack of contextual information. In this research, a single-shot detection algorithm based on cyclic attention (CA-SSD) is proposed to construct a fast and accurate detector that efficiently obtains full-image contextual information. Our network is constructed by integrating ResNet-34 and proposed novel cyclic attention blocks. This type of building block aggregates different transformations, one of which includes an attention module that uses a long but narrow pooling kernel to acquire horizontal and vertical contextual information for each pixel of all pixels. Each pixel eventually captures the full-image dependencies by following an even further cyclic operation. Our design considers the variability of the gradient, which not only improves the reliability of the cyclic attention block but also cuts the number of parameters for computation. Additionally, by exploring the effects of the stem block and its stride on the performance of ResNet-based SSD algorithms, our network retains more detailed information. For an input size of 300 <inline-formula< <tex-math notation="LaTeX"<$\times $ </tex-math<</inline-formula< 300, CA-SSD attained 82.5% mAP on PASCAL VOC 2007 test, 78.4% mAP on PASCAL VOC 2012 test, and 32.7% mAP on MS COCO. Experimental results achieved with CA-SSD surpass the best results achieved with the traditional SSD and other advanced object detection algorithms while real-time speed is maintained.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Object detection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">single-shot detector</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">ResNet</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">cyclic attention</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Electrical engineering. Electronics. Nuclear engineering</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Daochun Xu</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Jiangming Kan</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">IEEE Access</subfield><subfield code="d">IEEE, 2014</subfield><subfield code="g">9(2021), Seite 50557-50569</subfield><subfield code="w">(DE-627)728440385</subfield><subfield code="w">(DE-600)2687964-5</subfield><subfield code="x">21693536</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:9</subfield><subfield code="g">year:2021</subfield><subfield code="g">pages:50557-50569</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1109/ACCESS.2021.3068533</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/2bd8160d5d6c4234903386cce70f4c21</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://ieeexplore.ieee.org/document/9385111/</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2169-3536</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</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_39</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_63</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_95</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_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</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_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</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_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</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_4126</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_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_4335</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_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">9</subfield><subfield code="j">2021</subfield><subfield code="h">50557-50569</subfield></datafield></record></collection>
|
score |
7.400667 |