TAttMSRecNet:Triplet-attention and multiscale reconstruction network for band selection in hyperspectral images
The band selection (BS) is an essential task in hyperspectral images (HSIs), consisting of huge spectral bands with noises and redundancies. The attention mechanism can be used for BS. However, the existing attention-based BS schemes are failed to capture the cross-dimension interaction between the...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Nandi, Utpal [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2023transfer abstract |
|---|
| Schlagwörter: |
|---|
| Übergeordnetes Werk: |
Enthalten in: Do denture processing techniques affect the mechanical properties of denture teeth? - Clements, Jody L. ELSEVIER, 2017, an international journal, Amsterdam [u.a.] |
|---|---|
| Übergeordnetes Werk: |
volume:212 ; year:2023 ; pages:0 |
| Links: |
|---|
| DOI / URN: |
10.1016/j.eswa.2022.118797 |
|---|
| Katalog-ID: |
ELV05937084X |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | ELV05937084X | ||
| 003 | DE-627 | ||
| 005 | 20230626052739.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 221103s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.eswa.2022.118797 |2 doi | |
| 028 | 5 | 2 | |a /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001949.pica |
| 035 | |a (DE-627)ELV05937084X | ||
| 035 | |a (ELSEVIER)S0957-4174(22)01815-2 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 610 |q VZ |
| 084 | |a 44.96 |2 bkl | ||
| 100 | 1 | |a Nandi, Utpal |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a TAttMSRecNet:Triplet-attention and multiscale reconstruction network for band selection in hyperspectral images |
| 264 | 1 | |c 2023transfer abstract | |
| 336 | |a nicht spezifiziert |b zzz |2 rdacontent | ||
| 337 | |a nicht spezifiziert |b z |2 rdamedia | ||
| 338 | |a nicht spezifiziert |b zu |2 rdacarrier | ||
| 520 | |a The band selection (BS) is an essential task in hyperspectral images (HSIs), consisting of huge spectral bands with noises and redundancies. The attention mechanism can be used for BS. However, the existing attention-based BS schemes are failed to capture the cross-dimension interaction between the input spectral and spatial dimensions during computation of attention weights and may produce poor feature representations. Again, the used reconstruction network in the existing BS methods unable to detect the HSIs features in multiple scales by blindly increasing the depth of the network. To deal with these problems, a novel end-to-end unsupervised triplet-attention multiscale reconstruction network for BS (TAttMSRecNet) has been proposed. The proposed network utilizes a triplet-attention mechanism having three parallel branches responsible to aggregate interactive cross-dimensional features between the spatial and spectral dimensions. After that, the network restores the original HSIs by using a 3D multiscale reconstruction network that applies multiple size convolution kernels to capture the discriminative HSIs features over the multiple scales where these features also communicate themselves to find the most efficacious HSIs information. In this way, the rich features are captured at a little computation cost, and the most informative bands can be effectively chosen for classification. Three standard data sets — Indian Pines (IP), Salinas (SA), and University of Pavia (UP) have been taken to conduct the experiments. The presented TAttMSRecNet can efficiently suppress the redundant or useless bands and selects more informative bands for better classification performance and also outperforms the other existing BS methods. | ||
| 520 | |a The band selection (BS) is an essential task in hyperspectral images (HSIs), consisting of huge spectral bands with noises and redundancies. The attention mechanism can be used for BS. However, the existing attention-based BS schemes are failed to capture the cross-dimension interaction between the input spectral and spatial dimensions during computation of attention weights and may produce poor feature representations. Again, the used reconstruction network in the existing BS methods unable to detect the HSIs features in multiple scales by blindly increasing the depth of the network. To deal with these problems, a novel end-to-end unsupervised triplet-attention multiscale reconstruction network for BS (TAttMSRecNet) has been proposed. The proposed network utilizes a triplet-attention mechanism having three parallel branches responsible to aggregate interactive cross-dimensional features between the spatial and spectral dimensions. After that, the network restores the original HSIs by using a 3D multiscale reconstruction network that applies multiple size convolution kernels to capture the discriminative HSIs features over the multiple scales where these features also communicate themselves to find the most efficacious HSIs information. In this way, the rich features are captured at a little computation cost, and the most informative bands can be effectively chosen for classification. Three standard data sets — Indian Pines (IP), Salinas (SA), and University of Pavia (UP) have been taken to conduct the experiments. The presented TAttMSRecNet can efficiently suppress the redundant or useless bands and selects more informative bands for better classification performance and also outperforms the other existing BS methods. | ||
| 650 | 7 | |a Hyperspectral images (HSIs) |2 Elsevier | |
| 650 | 7 | |a Band selection (BS) |2 Elsevier | |
| 650 | 7 | |a Multiscale reconstruction network |2 Elsevier | |
| 650 | 7 | |a Triplet attention |2 Elsevier | |
| 700 | 1 | |a Roy, Swalpa Kumar |4 oth | |
| 700 | 1 | |a Hong, Danfeng |4 oth | |
| 700 | 1 | |a Wu, Xin |4 oth | |
| 700 | 1 | |a Chanussot, Jocelyn |4 oth | |
| 773 | 0 | 8 | |i Enthalten in |n Elsevier Science |a Clements, Jody L. ELSEVIER |t Do denture processing techniques affect the mechanical properties of denture teeth? |d 2017 |d an international journal |g Amsterdam [u.a.] |w (DE-627)ELV000222070 |
| 773 | 1 | 8 | |g volume:212 |g year:2023 |g pages:0 |
| 856 | 4 | 0 | |u https://doi.org/10.1016/j.eswa.2022.118797 |3 Volltext |
| 912 | |a GBV_USEFLAG_U | ||
| 912 | |a GBV_ELV | ||
| 912 | |a SYSFLAG_U | ||
| 912 | |a SSG-OLC-PHA | ||
| 936 | b | k | |a 44.96 |j Zahnmedizin |q VZ |
| 951 | |a AR | ||
| 952 | |d 212 |j 2023 |h 0 | ||
| author_variant |
u n un |
|---|---|
| matchkey_str |
nandiutpalroyswalpakumarhongdanfengwuxin:2023----:atsentrpeatninnmliclrcntutontokobnsl |
| hierarchy_sort_str |
2023transfer abstract |
| bklnumber |
44.96 |
| publishDate |
2023 |
| allfields |
10.1016/j.eswa.2022.118797 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001949.pica (DE-627)ELV05937084X (ELSEVIER)S0957-4174(22)01815-2 DE-627 ger DE-627 rakwb eng 610 VZ 44.96 bkl Nandi, Utpal verfasserin aut TAttMSRecNet:Triplet-attention and multiscale reconstruction network for band selection in hyperspectral images 2023transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier The band selection (BS) is an essential task in hyperspectral images (HSIs), consisting of huge spectral bands with noises and redundancies. The attention mechanism can be used for BS. However, the existing attention-based BS schemes are failed to capture the cross-dimension interaction between the input spectral and spatial dimensions during computation of attention weights and may produce poor feature representations. Again, the used reconstruction network in the existing BS methods unable to detect the HSIs features in multiple scales by blindly increasing the depth of the network. To deal with these problems, a novel end-to-end unsupervised triplet-attention multiscale reconstruction network for BS (TAttMSRecNet) has been proposed. The proposed network utilizes a triplet-attention mechanism having three parallel branches responsible to aggregate interactive cross-dimensional features between the spatial and spectral dimensions. After that, the network restores the original HSIs by using a 3D multiscale reconstruction network that applies multiple size convolution kernels to capture the discriminative HSIs features over the multiple scales where these features also communicate themselves to find the most efficacious HSIs information. In this way, the rich features are captured at a little computation cost, and the most informative bands can be effectively chosen for classification. Three standard data sets — Indian Pines (IP), Salinas (SA), and University of Pavia (UP) have been taken to conduct the experiments. The presented TAttMSRecNet can efficiently suppress the redundant or useless bands and selects more informative bands for better classification performance and also outperforms the other existing BS methods. The band selection (BS) is an essential task in hyperspectral images (HSIs), consisting of huge spectral bands with noises and redundancies. The attention mechanism can be used for BS. However, the existing attention-based BS schemes are failed to capture the cross-dimension interaction between the input spectral and spatial dimensions during computation of attention weights and may produce poor feature representations. Again, the used reconstruction network in the existing BS methods unable to detect the HSIs features in multiple scales by blindly increasing the depth of the network. To deal with these problems, a novel end-to-end unsupervised triplet-attention multiscale reconstruction network for BS (TAttMSRecNet) has been proposed. The proposed network utilizes a triplet-attention mechanism having three parallel branches responsible to aggregate interactive cross-dimensional features between the spatial and spectral dimensions. After that, the network restores the original HSIs by using a 3D multiscale reconstruction network that applies multiple size convolution kernels to capture the discriminative HSIs features over the multiple scales where these features also communicate themselves to find the most efficacious HSIs information. In this way, the rich features are captured at a little computation cost, and the most informative bands can be effectively chosen for classification. Three standard data sets — Indian Pines (IP), Salinas (SA), and University of Pavia (UP) have been taken to conduct the experiments. The presented TAttMSRecNet can efficiently suppress the redundant or useless bands and selects more informative bands for better classification performance and also outperforms the other existing BS methods. Hyperspectral images (HSIs) Elsevier Band selection (BS) Elsevier Multiscale reconstruction network Elsevier Triplet attention Elsevier Roy, Swalpa Kumar oth Hong, Danfeng oth Wu, Xin oth Chanussot, Jocelyn oth Enthalten in Elsevier Science Clements, Jody L. ELSEVIER Do denture processing techniques affect the mechanical properties of denture teeth? 2017 an international journal Amsterdam [u.a.] (DE-627)ELV000222070 volume:212 year:2023 pages:0 https://doi.org/10.1016/j.eswa.2022.118797 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA 44.96 Zahnmedizin VZ AR 212 2023 0 |
| spelling |
10.1016/j.eswa.2022.118797 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001949.pica (DE-627)ELV05937084X (ELSEVIER)S0957-4174(22)01815-2 DE-627 ger DE-627 rakwb eng 610 VZ 44.96 bkl Nandi, Utpal verfasserin aut TAttMSRecNet:Triplet-attention and multiscale reconstruction network for band selection in hyperspectral images 2023transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier The band selection (BS) is an essential task in hyperspectral images (HSIs), consisting of huge spectral bands with noises and redundancies. The attention mechanism can be used for BS. However, the existing attention-based BS schemes are failed to capture the cross-dimension interaction between the input spectral and spatial dimensions during computation of attention weights and may produce poor feature representations. Again, the used reconstruction network in the existing BS methods unable to detect the HSIs features in multiple scales by blindly increasing the depth of the network. To deal with these problems, a novel end-to-end unsupervised triplet-attention multiscale reconstruction network for BS (TAttMSRecNet) has been proposed. The proposed network utilizes a triplet-attention mechanism having three parallel branches responsible to aggregate interactive cross-dimensional features between the spatial and spectral dimensions. After that, the network restores the original HSIs by using a 3D multiscale reconstruction network that applies multiple size convolution kernels to capture the discriminative HSIs features over the multiple scales where these features also communicate themselves to find the most efficacious HSIs information. In this way, the rich features are captured at a little computation cost, and the most informative bands can be effectively chosen for classification. Three standard data sets — Indian Pines (IP), Salinas (SA), and University of Pavia (UP) have been taken to conduct the experiments. The presented TAttMSRecNet can efficiently suppress the redundant or useless bands and selects more informative bands for better classification performance and also outperforms the other existing BS methods. The band selection (BS) is an essential task in hyperspectral images (HSIs), consisting of huge spectral bands with noises and redundancies. The attention mechanism can be used for BS. However, the existing attention-based BS schemes are failed to capture the cross-dimension interaction between the input spectral and spatial dimensions during computation of attention weights and may produce poor feature representations. Again, the used reconstruction network in the existing BS methods unable to detect the HSIs features in multiple scales by blindly increasing the depth of the network. To deal with these problems, a novel end-to-end unsupervised triplet-attention multiscale reconstruction network for BS (TAttMSRecNet) has been proposed. The proposed network utilizes a triplet-attention mechanism having three parallel branches responsible to aggregate interactive cross-dimensional features between the spatial and spectral dimensions. After that, the network restores the original HSIs by using a 3D multiscale reconstruction network that applies multiple size convolution kernels to capture the discriminative HSIs features over the multiple scales where these features also communicate themselves to find the most efficacious HSIs information. In this way, the rich features are captured at a little computation cost, and the most informative bands can be effectively chosen for classification. Three standard data sets — Indian Pines (IP), Salinas (SA), and University of Pavia (UP) have been taken to conduct the experiments. The presented TAttMSRecNet can efficiently suppress the redundant or useless bands and selects more informative bands for better classification performance and also outperforms the other existing BS methods. Hyperspectral images (HSIs) Elsevier Band selection (BS) Elsevier Multiscale reconstruction network Elsevier Triplet attention Elsevier Roy, Swalpa Kumar oth Hong, Danfeng oth Wu, Xin oth Chanussot, Jocelyn oth Enthalten in Elsevier Science Clements, Jody L. ELSEVIER Do denture processing techniques affect the mechanical properties of denture teeth? 2017 an international journal Amsterdam [u.a.] (DE-627)ELV000222070 volume:212 year:2023 pages:0 https://doi.org/10.1016/j.eswa.2022.118797 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA 44.96 Zahnmedizin VZ AR 212 2023 0 |
| allfields_unstemmed |
10.1016/j.eswa.2022.118797 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001949.pica (DE-627)ELV05937084X (ELSEVIER)S0957-4174(22)01815-2 DE-627 ger DE-627 rakwb eng 610 VZ 44.96 bkl Nandi, Utpal verfasserin aut TAttMSRecNet:Triplet-attention and multiscale reconstruction network for band selection in hyperspectral images 2023transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier The band selection (BS) is an essential task in hyperspectral images (HSIs), consisting of huge spectral bands with noises and redundancies. The attention mechanism can be used for BS. However, the existing attention-based BS schemes are failed to capture the cross-dimension interaction between the input spectral and spatial dimensions during computation of attention weights and may produce poor feature representations. Again, the used reconstruction network in the existing BS methods unable to detect the HSIs features in multiple scales by blindly increasing the depth of the network. To deal with these problems, a novel end-to-end unsupervised triplet-attention multiscale reconstruction network for BS (TAttMSRecNet) has been proposed. The proposed network utilizes a triplet-attention mechanism having three parallel branches responsible to aggregate interactive cross-dimensional features between the spatial and spectral dimensions. After that, the network restores the original HSIs by using a 3D multiscale reconstruction network that applies multiple size convolution kernels to capture the discriminative HSIs features over the multiple scales where these features also communicate themselves to find the most efficacious HSIs information. In this way, the rich features are captured at a little computation cost, and the most informative bands can be effectively chosen for classification. Three standard data sets — Indian Pines (IP), Salinas (SA), and University of Pavia (UP) have been taken to conduct the experiments. The presented TAttMSRecNet can efficiently suppress the redundant or useless bands and selects more informative bands for better classification performance and also outperforms the other existing BS methods. The band selection (BS) is an essential task in hyperspectral images (HSIs), consisting of huge spectral bands with noises and redundancies. The attention mechanism can be used for BS. However, the existing attention-based BS schemes are failed to capture the cross-dimension interaction between the input spectral and spatial dimensions during computation of attention weights and may produce poor feature representations. Again, the used reconstruction network in the existing BS methods unable to detect the HSIs features in multiple scales by blindly increasing the depth of the network. To deal with these problems, a novel end-to-end unsupervised triplet-attention multiscale reconstruction network for BS (TAttMSRecNet) has been proposed. The proposed network utilizes a triplet-attention mechanism having three parallel branches responsible to aggregate interactive cross-dimensional features between the spatial and spectral dimensions. After that, the network restores the original HSIs by using a 3D multiscale reconstruction network that applies multiple size convolution kernels to capture the discriminative HSIs features over the multiple scales where these features also communicate themselves to find the most efficacious HSIs information. In this way, the rich features are captured at a little computation cost, and the most informative bands can be effectively chosen for classification. Three standard data sets — Indian Pines (IP), Salinas (SA), and University of Pavia (UP) have been taken to conduct the experiments. The presented TAttMSRecNet can efficiently suppress the redundant or useless bands and selects more informative bands for better classification performance and also outperforms the other existing BS methods. Hyperspectral images (HSIs) Elsevier Band selection (BS) Elsevier Multiscale reconstruction network Elsevier Triplet attention Elsevier Roy, Swalpa Kumar oth Hong, Danfeng oth Wu, Xin oth Chanussot, Jocelyn oth Enthalten in Elsevier Science Clements, Jody L. ELSEVIER Do denture processing techniques affect the mechanical properties of denture teeth? 2017 an international journal Amsterdam [u.a.] (DE-627)ELV000222070 volume:212 year:2023 pages:0 https://doi.org/10.1016/j.eswa.2022.118797 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA 44.96 Zahnmedizin VZ AR 212 2023 0 |
| allfieldsGer |
10.1016/j.eswa.2022.118797 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001949.pica (DE-627)ELV05937084X (ELSEVIER)S0957-4174(22)01815-2 DE-627 ger DE-627 rakwb eng 610 VZ 44.96 bkl Nandi, Utpal verfasserin aut TAttMSRecNet:Triplet-attention and multiscale reconstruction network for band selection in hyperspectral images 2023transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier The band selection (BS) is an essential task in hyperspectral images (HSIs), consisting of huge spectral bands with noises and redundancies. The attention mechanism can be used for BS. However, the existing attention-based BS schemes are failed to capture the cross-dimension interaction between the input spectral and spatial dimensions during computation of attention weights and may produce poor feature representations. Again, the used reconstruction network in the existing BS methods unable to detect the HSIs features in multiple scales by blindly increasing the depth of the network. To deal with these problems, a novel end-to-end unsupervised triplet-attention multiscale reconstruction network for BS (TAttMSRecNet) has been proposed. The proposed network utilizes a triplet-attention mechanism having three parallel branches responsible to aggregate interactive cross-dimensional features between the spatial and spectral dimensions. After that, the network restores the original HSIs by using a 3D multiscale reconstruction network that applies multiple size convolution kernels to capture the discriminative HSIs features over the multiple scales where these features also communicate themselves to find the most efficacious HSIs information. In this way, the rich features are captured at a little computation cost, and the most informative bands can be effectively chosen for classification. Three standard data sets — Indian Pines (IP), Salinas (SA), and University of Pavia (UP) have been taken to conduct the experiments. The presented TAttMSRecNet can efficiently suppress the redundant or useless bands and selects more informative bands for better classification performance and also outperforms the other existing BS methods. The band selection (BS) is an essential task in hyperspectral images (HSIs), consisting of huge spectral bands with noises and redundancies. The attention mechanism can be used for BS. However, the existing attention-based BS schemes are failed to capture the cross-dimension interaction between the input spectral and spatial dimensions during computation of attention weights and may produce poor feature representations. Again, the used reconstruction network in the existing BS methods unable to detect the HSIs features in multiple scales by blindly increasing the depth of the network. To deal with these problems, a novel end-to-end unsupervised triplet-attention multiscale reconstruction network for BS (TAttMSRecNet) has been proposed. The proposed network utilizes a triplet-attention mechanism having three parallel branches responsible to aggregate interactive cross-dimensional features between the spatial and spectral dimensions. After that, the network restores the original HSIs by using a 3D multiscale reconstruction network that applies multiple size convolution kernels to capture the discriminative HSIs features over the multiple scales where these features also communicate themselves to find the most efficacious HSIs information. In this way, the rich features are captured at a little computation cost, and the most informative bands can be effectively chosen for classification. Three standard data sets — Indian Pines (IP), Salinas (SA), and University of Pavia (UP) have been taken to conduct the experiments. The presented TAttMSRecNet can efficiently suppress the redundant or useless bands and selects more informative bands for better classification performance and also outperforms the other existing BS methods. Hyperspectral images (HSIs) Elsevier Band selection (BS) Elsevier Multiscale reconstruction network Elsevier Triplet attention Elsevier Roy, Swalpa Kumar oth Hong, Danfeng oth Wu, Xin oth Chanussot, Jocelyn oth Enthalten in Elsevier Science Clements, Jody L. ELSEVIER Do denture processing techniques affect the mechanical properties of denture teeth? 2017 an international journal Amsterdam [u.a.] (DE-627)ELV000222070 volume:212 year:2023 pages:0 https://doi.org/10.1016/j.eswa.2022.118797 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA 44.96 Zahnmedizin VZ AR 212 2023 0 |
| allfieldsSound |
10.1016/j.eswa.2022.118797 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001949.pica (DE-627)ELV05937084X (ELSEVIER)S0957-4174(22)01815-2 DE-627 ger DE-627 rakwb eng 610 VZ 44.96 bkl Nandi, Utpal verfasserin aut TAttMSRecNet:Triplet-attention and multiscale reconstruction network for band selection in hyperspectral images 2023transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier The band selection (BS) is an essential task in hyperspectral images (HSIs), consisting of huge spectral bands with noises and redundancies. The attention mechanism can be used for BS. However, the existing attention-based BS schemes are failed to capture the cross-dimension interaction between the input spectral and spatial dimensions during computation of attention weights and may produce poor feature representations. Again, the used reconstruction network in the existing BS methods unable to detect the HSIs features in multiple scales by blindly increasing the depth of the network. To deal with these problems, a novel end-to-end unsupervised triplet-attention multiscale reconstruction network for BS (TAttMSRecNet) has been proposed. The proposed network utilizes a triplet-attention mechanism having three parallel branches responsible to aggregate interactive cross-dimensional features between the spatial and spectral dimensions. After that, the network restores the original HSIs by using a 3D multiscale reconstruction network that applies multiple size convolution kernels to capture the discriminative HSIs features over the multiple scales where these features also communicate themselves to find the most efficacious HSIs information. In this way, the rich features are captured at a little computation cost, and the most informative bands can be effectively chosen for classification. Three standard data sets — Indian Pines (IP), Salinas (SA), and University of Pavia (UP) have been taken to conduct the experiments. The presented TAttMSRecNet can efficiently suppress the redundant or useless bands and selects more informative bands for better classification performance and also outperforms the other existing BS methods. The band selection (BS) is an essential task in hyperspectral images (HSIs), consisting of huge spectral bands with noises and redundancies. The attention mechanism can be used for BS. However, the existing attention-based BS schemes are failed to capture the cross-dimension interaction between the input spectral and spatial dimensions during computation of attention weights and may produce poor feature representations. Again, the used reconstruction network in the existing BS methods unable to detect the HSIs features in multiple scales by blindly increasing the depth of the network. To deal with these problems, a novel end-to-end unsupervised triplet-attention multiscale reconstruction network for BS (TAttMSRecNet) has been proposed. The proposed network utilizes a triplet-attention mechanism having three parallel branches responsible to aggregate interactive cross-dimensional features between the spatial and spectral dimensions. After that, the network restores the original HSIs by using a 3D multiscale reconstruction network that applies multiple size convolution kernels to capture the discriminative HSIs features over the multiple scales where these features also communicate themselves to find the most efficacious HSIs information. In this way, the rich features are captured at a little computation cost, and the most informative bands can be effectively chosen for classification. Three standard data sets — Indian Pines (IP), Salinas (SA), and University of Pavia (UP) have been taken to conduct the experiments. The presented TAttMSRecNet can efficiently suppress the redundant or useless bands and selects more informative bands for better classification performance and also outperforms the other existing BS methods. Hyperspectral images (HSIs) Elsevier Band selection (BS) Elsevier Multiscale reconstruction network Elsevier Triplet attention Elsevier Roy, Swalpa Kumar oth Hong, Danfeng oth Wu, Xin oth Chanussot, Jocelyn oth Enthalten in Elsevier Science Clements, Jody L. ELSEVIER Do denture processing techniques affect the mechanical properties of denture teeth? 2017 an international journal Amsterdam [u.a.] (DE-627)ELV000222070 volume:212 year:2023 pages:0 https://doi.org/10.1016/j.eswa.2022.118797 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA 44.96 Zahnmedizin VZ AR 212 2023 0 |
| language |
English |
| source |
Enthalten in Do denture processing techniques affect the mechanical properties of denture teeth? Amsterdam [u.a.] volume:212 year:2023 pages:0 |
| sourceStr |
Enthalten in Do denture processing techniques affect the mechanical properties of denture teeth? Amsterdam [u.a.] volume:212 year:2023 pages:0 |
| format_phy_str_mv |
Article |
| bklname |
Zahnmedizin |
| institution |
findex.gbv.de |
| topic_facet |
Hyperspectral images (HSIs) Band selection (BS) Multiscale reconstruction network Triplet attention |
| dewey-raw |
610 |
| isfreeaccess_bool |
false |
| container_title |
Do denture processing techniques affect the mechanical properties of denture teeth? |
| authorswithroles_txt_mv |
Nandi, Utpal @@aut@@ Roy, Swalpa Kumar @@oth@@ Hong, Danfeng @@oth@@ Wu, Xin @@oth@@ Chanussot, Jocelyn @@oth@@ |
| publishDateDaySort_date |
2023-01-01T00:00:00Z |
| hierarchy_top_id |
ELV000222070 |
| dewey-sort |
3610 |
| id |
ELV05937084X |
| 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">ELV05937084X</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626052739.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">221103s2023 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.eswa.2022.118797</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">/cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001949.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV05937084X</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0957-4174(22)01815-2</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="082" ind1="0" ind2="4"><subfield code="a">610</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">44.96</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Nandi, Utpal</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">TAttMSRecNet:Triplet-attention and multiscale reconstruction network for band selection in hyperspectral images</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023transfer abstract</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">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">The band selection (BS) is an essential task in hyperspectral images (HSIs), consisting of huge spectral bands with noises and redundancies. The attention mechanism can be used for BS. However, the existing attention-based BS schemes are failed to capture the cross-dimension interaction between the input spectral and spatial dimensions during computation of attention weights and may produce poor feature representations. Again, the used reconstruction network in the existing BS methods unable to detect the HSIs features in multiple scales by blindly increasing the depth of the network. To deal with these problems, a novel end-to-end unsupervised triplet-attention multiscale reconstruction network for BS (TAttMSRecNet) has been proposed. The proposed network utilizes a triplet-attention mechanism having three parallel branches responsible to aggregate interactive cross-dimensional features between the spatial and spectral dimensions. After that, the network restores the original HSIs by using a 3D multiscale reconstruction network that applies multiple size convolution kernels to capture the discriminative HSIs features over the multiple scales where these features also communicate themselves to find the most efficacious HSIs information. In this way, the rich features are captured at a little computation cost, and the most informative bands can be effectively chosen for classification. Three standard data sets — Indian Pines (IP), Salinas (SA), and University of Pavia (UP) have been taken to conduct the experiments. The presented TAttMSRecNet can efficiently suppress the redundant or useless bands and selects more informative bands for better classification performance and also outperforms the other existing BS methods.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">The band selection (BS) is an essential task in hyperspectral images (HSIs), consisting of huge spectral bands with noises and redundancies. The attention mechanism can be used for BS. However, the existing attention-based BS schemes are failed to capture the cross-dimension interaction between the input spectral and spatial dimensions during computation of attention weights and may produce poor feature representations. Again, the used reconstruction network in the existing BS methods unable to detect the HSIs features in multiple scales by blindly increasing the depth of the network. To deal with these problems, a novel end-to-end unsupervised triplet-attention multiscale reconstruction network for BS (TAttMSRecNet) has been proposed. The proposed network utilizes a triplet-attention mechanism having three parallel branches responsible to aggregate interactive cross-dimensional features between the spatial and spectral dimensions. After that, the network restores the original HSIs by using a 3D multiscale reconstruction network that applies multiple size convolution kernels to capture the discriminative HSIs features over the multiple scales where these features also communicate themselves to find the most efficacious HSIs information. In this way, the rich features are captured at a little computation cost, and the most informative bands can be effectively chosen for classification. Three standard data sets — Indian Pines (IP), Salinas (SA), and University of Pavia (UP) have been taken to conduct the experiments. The presented TAttMSRecNet can efficiently suppress the redundant or useless bands and selects more informative bands for better classification performance and also outperforms the other existing BS methods.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Hyperspectral images (HSIs)</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Band selection (BS)</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Multiscale reconstruction network</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Triplet attention</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Roy, Swalpa Kumar</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Hong, Danfeng</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wu, Xin</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Chanussot, Jocelyn</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier Science</subfield><subfield code="a">Clements, Jody L. ELSEVIER</subfield><subfield code="t">Do denture processing techniques affect the mechanical properties of denture teeth?</subfield><subfield code="d">2017</subfield><subfield code="d">an international journal</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV000222070</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:212</subfield><subfield code="g">year:2023</subfield><subfield code="g">pages:0</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.eswa.2022.118797</subfield><subfield code="3">Volltext</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">SSG-OLC-PHA</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">44.96</subfield><subfield code="j">Zahnmedizin</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">212</subfield><subfield code="j">2023</subfield><subfield code="h">0</subfield></datafield></record></collection>
|
| author |
Nandi, Utpal |
| spellingShingle |
Nandi, Utpal ddc 610 bkl 44.96 Elsevier Hyperspectral images (HSIs) Elsevier Band selection (BS) Elsevier Multiscale reconstruction network Elsevier Triplet attention TAttMSRecNet:Triplet-attention and multiscale reconstruction network for band selection in hyperspectral images |
| authorStr |
Nandi, Utpal |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)ELV000222070 |
| format |
electronic Article |
| dewey-ones |
610 - Medicine & health |
| delete_txt_mv |
keep |
| author_role |
aut |
| collection |
elsevier |
| remote_str |
true |
| illustrated |
Not Illustrated |
| topic_title |
610 VZ 44.96 bkl TAttMSRecNet:Triplet-attention and multiscale reconstruction network for band selection in hyperspectral images Hyperspectral images (HSIs) Elsevier Band selection (BS) Elsevier Multiscale reconstruction network Elsevier Triplet attention Elsevier |
| topic |
ddc 610 bkl 44.96 Elsevier Hyperspectral images (HSIs) Elsevier Band selection (BS) Elsevier Multiscale reconstruction network Elsevier Triplet attention |
| topic_unstemmed |
ddc 610 bkl 44.96 Elsevier Hyperspectral images (HSIs) Elsevier Band selection (BS) Elsevier Multiscale reconstruction network Elsevier Triplet attention |
| topic_browse |
ddc 610 bkl 44.96 Elsevier Hyperspectral images (HSIs) Elsevier Band selection (BS) Elsevier Multiscale reconstruction network Elsevier Triplet attention |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
zu |
| author2_variant |
s k r sk skr d h dh x w xw j c jc |
| hierarchy_parent_title |
Do denture processing techniques affect the mechanical properties of denture teeth? |
| hierarchy_parent_id |
ELV000222070 |
| dewey-tens |
610 - Medicine & health |
| hierarchy_top_title |
Do denture processing techniques affect the mechanical properties of denture teeth? |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)ELV000222070 |
| title |
TAttMSRecNet:Triplet-attention and multiscale reconstruction network for band selection in hyperspectral images |
| ctrlnum |
(DE-627)ELV05937084X (ELSEVIER)S0957-4174(22)01815-2 |
| title_full |
TAttMSRecNet:Triplet-attention and multiscale reconstruction network for band selection in hyperspectral images |
| author_sort |
Nandi, Utpal |
| journal |
Do denture processing techniques affect the mechanical properties of denture teeth? |
| journalStr |
Do denture processing techniques affect the mechanical properties of denture teeth? |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
600 - Technology |
| recordtype |
marc |
| publishDateSort |
2023 |
| contenttype_str_mv |
zzz |
| container_start_page |
0 |
| author_browse |
Nandi, Utpal |
| container_volume |
212 |
| class |
610 VZ 44.96 bkl |
| format_se |
Elektronische Aufsätze |
| author-letter |
Nandi, Utpal |
| doi_str_mv |
10.1016/j.eswa.2022.118797 |
| dewey-full |
610 |
| title_sort |
tattmsrecnet:triplet-attention and multiscale reconstruction network for band selection in hyperspectral images |
| title_auth |
TAttMSRecNet:Triplet-attention and multiscale reconstruction network for band selection in hyperspectral images |
| abstract |
The band selection (BS) is an essential task in hyperspectral images (HSIs), consisting of huge spectral bands with noises and redundancies. The attention mechanism can be used for BS. However, the existing attention-based BS schemes are failed to capture the cross-dimension interaction between the input spectral and spatial dimensions during computation of attention weights and may produce poor feature representations. Again, the used reconstruction network in the existing BS methods unable to detect the HSIs features in multiple scales by blindly increasing the depth of the network. To deal with these problems, a novel end-to-end unsupervised triplet-attention multiscale reconstruction network for BS (TAttMSRecNet) has been proposed. The proposed network utilizes a triplet-attention mechanism having three parallel branches responsible to aggregate interactive cross-dimensional features between the spatial and spectral dimensions. After that, the network restores the original HSIs by using a 3D multiscale reconstruction network that applies multiple size convolution kernels to capture the discriminative HSIs features over the multiple scales where these features also communicate themselves to find the most efficacious HSIs information. In this way, the rich features are captured at a little computation cost, and the most informative bands can be effectively chosen for classification. Three standard data sets — Indian Pines (IP), Salinas (SA), and University of Pavia (UP) have been taken to conduct the experiments. The presented TAttMSRecNet can efficiently suppress the redundant or useless bands and selects more informative bands for better classification performance and also outperforms the other existing BS methods. |
| abstractGer |
The band selection (BS) is an essential task in hyperspectral images (HSIs), consisting of huge spectral bands with noises and redundancies. The attention mechanism can be used for BS. However, the existing attention-based BS schemes are failed to capture the cross-dimension interaction between the input spectral and spatial dimensions during computation of attention weights and may produce poor feature representations. Again, the used reconstruction network in the existing BS methods unable to detect the HSIs features in multiple scales by blindly increasing the depth of the network. To deal with these problems, a novel end-to-end unsupervised triplet-attention multiscale reconstruction network for BS (TAttMSRecNet) has been proposed. The proposed network utilizes a triplet-attention mechanism having three parallel branches responsible to aggregate interactive cross-dimensional features between the spatial and spectral dimensions. After that, the network restores the original HSIs by using a 3D multiscale reconstruction network that applies multiple size convolution kernels to capture the discriminative HSIs features over the multiple scales where these features also communicate themselves to find the most efficacious HSIs information. In this way, the rich features are captured at a little computation cost, and the most informative bands can be effectively chosen for classification. Three standard data sets — Indian Pines (IP), Salinas (SA), and University of Pavia (UP) have been taken to conduct the experiments. The presented TAttMSRecNet can efficiently suppress the redundant or useless bands and selects more informative bands for better classification performance and also outperforms the other existing BS methods. |
| abstract_unstemmed |
The band selection (BS) is an essential task in hyperspectral images (HSIs), consisting of huge spectral bands with noises and redundancies. The attention mechanism can be used for BS. However, the existing attention-based BS schemes are failed to capture the cross-dimension interaction between the input spectral and spatial dimensions during computation of attention weights and may produce poor feature representations. Again, the used reconstruction network in the existing BS methods unable to detect the HSIs features in multiple scales by blindly increasing the depth of the network. To deal with these problems, a novel end-to-end unsupervised triplet-attention multiscale reconstruction network for BS (TAttMSRecNet) has been proposed. The proposed network utilizes a triplet-attention mechanism having three parallel branches responsible to aggregate interactive cross-dimensional features between the spatial and spectral dimensions. After that, the network restores the original HSIs by using a 3D multiscale reconstruction network that applies multiple size convolution kernels to capture the discriminative HSIs features over the multiple scales where these features also communicate themselves to find the most efficacious HSIs information. In this way, the rich features are captured at a little computation cost, and the most informative bands can be effectively chosen for classification. Three standard data sets — Indian Pines (IP), Salinas (SA), and University of Pavia (UP) have been taken to conduct the experiments. The presented TAttMSRecNet can efficiently suppress the redundant or useless bands and selects more informative bands for better classification performance and also outperforms the other existing BS methods. |
| collection_details |
GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA |
| title_short |
TAttMSRecNet:Triplet-attention and multiscale reconstruction network for band selection in hyperspectral images |
| url |
https://doi.org/10.1016/j.eswa.2022.118797 |
| remote_bool |
true |
| author2 |
Roy, Swalpa Kumar Hong, Danfeng Wu, Xin Chanussot, Jocelyn |
| author2Str |
Roy, Swalpa Kumar Hong, Danfeng Wu, Xin Chanussot, Jocelyn |
| ppnlink |
ELV000222070 |
| mediatype_str_mv |
z |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| author2_role |
oth oth oth oth |
| doi_str |
10.1016/j.eswa.2022.118797 |
| up_date |
2024-07-06T21:47:30.139Z |
| _version_ |
1803867861958000640 |
| 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">ELV05937084X</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626052739.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">221103s2023 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.eswa.2022.118797</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">/cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001949.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV05937084X</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0957-4174(22)01815-2</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="082" ind1="0" ind2="4"><subfield code="a">610</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">44.96</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Nandi, Utpal</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">TAttMSRecNet:Triplet-attention and multiscale reconstruction network for band selection in hyperspectral images</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023transfer abstract</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">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">The band selection (BS) is an essential task in hyperspectral images (HSIs), consisting of huge spectral bands with noises and redundancies. The attention mechanism can be used for BS. However, the existing attention-based BS schemes are failed to capture the cross-dimension interaction between the input spectral and spatial dimensions during computation of attention weights and may produce poor feature representations. Again, the used reconstruction network in the existing BS methods unable to detect the HSIs features in multiple scales by blindly increasing the depth of the network. To deal with these problems, a novel end-to-end unsupervised triplet-attention multiscale reconstruction network for BS (TAttMSRecNet) has been proposed. The proposed network utilizes a triplet-attention mechanism having three parallel branches responsible to aggregate interactive cross-dimensional features between the spatial and spectral dimensions. After that, the network restores the original HSIs by using a 3D multiscale reconstruction network that applies multiple size convolution kernels to capture the discriminative HSIs features over the multiple scales where these features also communicate themselves to find the most efficacious HSIs information. In this way, the rich features are captured at a little computation cost, and the most informative bands can be effectively chosen for classification. Three standard data sets — Indian Pines (IP), Salinas (SA), and University of Pavia (UP) have been taken to conduct the experiments. The presented TAttMSRecNet can efficiently suppress the redundant or useless bands and selects more informative bands for better classification performance and also outperforms the other existing BS methods.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">The band selection (BS) is an essential task in hyperspectral images (HSIs), consisting of huge spectral bands with noises and redundancies. The attention mechanism can be used for BS. However, the existing attention-based BS schemes are failed to capture the cross-dimension interaction between the input spectral and spatial dimensions during computation of attention weights and may produce poor feature representations. Again, the used reconstruction network in the existing BS methods unable to detect the HSIs features in multiple scales by blindly increasing the depth of the network. To deal with these problems, a novel end-to-end unsupervised triplet-attention multiscale reconstruction network for BS (TAttMSRecNet) has been proposed. The proposed network utilizes a triplet-attention mechanism having three parallel branches responsible to aggregate interactive cross-dimensional features between the spatial and spectral dimensions. After that, the network restores the original HSIs by using a 3D multiscale reconstruction network that applies multiple size convolution kernels to capture the discriminative HSIs features over the multiple scales where these features also communicate themselves to find the most efficacious HSIs information. In this way, the rich features are captured at a little computation cost, and the most informative bands can be effectively chosen for classification. Three standard data sets — Indian Pines (IP), Salinas (SA), and University of Pavia (UP) have been taken to conduct the experiments. The presented TAttMSRecNet can efficiently suppress the redundant or useless bands and selects more informative bands for better classification performance and also outperforms the other existing BS methods.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Hyperspectral images (HSIs)</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Band selection (BS)</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Multiscale reconstruction network</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Triplet attention</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Roy, Swalpa Kumar</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Hong, Danfeng</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wu, Xin</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Chanussot, Jocelyn</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier Science</subfield><subfield code="a">Clements, Jody L. ELSEVIER</subfield><subfield code="t">Do denture processing techniques affect the mechanical properties of denture teeth?</subfield><subfield code="d">2017</subfield><subfield code="d">an international journal</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV000222070</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:212</subfield><subfield code="g">year:2023</subfield><subfield code="g">pages:0</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.eswa.2022.118797</subfield><subfield code="3">Volltext</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">SSG-OLC-PHA</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">44.96</subfield><subfield code="j">Zahnmedizin</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">212</subfield><subfield code="j">2023</subfield><subfield code="h">0</subfield></datafield></record></collection>
|
| score |
7.4012985 |