Matches in SemOpenAlex for { <https://semopenalex.org/work/W4206550078> ?p ?o ?g. }
- W4206550078 endingPage "14" @default.
- W4206550078 startingPage "1" @default.
- W4206550078 abstract "Hyperspectral images (HSIs) contain rich spectral signatures that reveal more image details and, thus, enable the detection of less noticeable changes on the ground. However, HSI-based change detection (CD) is susceptible to a large amount of irrelevant or noisy spectral and spatial information due to massive spectral bands. To address these issues, we propose a novel spectral and spatial attention network (S<sup>2</sup>AN) for HSI-based CD, which is capable to suppress CD-irrelevant spectral and spatial information via adaptive spectral and spatial attention mechanisms. S<sup>2</sup>AN takes as input the image patch from the difference map between two HSIs and outputs the status of change for the patch. Specifically, S<sup>2</sup>AN is composed of several repeated attention blocks, each of which contains the spectral attention (SpeA) module for directly calculating the attention score for each input channel, the Gaussian spatial attention (GSpaA) module that first constructs an adaptive Gaussian distribution and then samples it to derive the attention scores for each spatial position, and the convolutional feature extraction (CFE) module for extracting features from the attention-weighted input. It is worth mentioning that, in addition to the advantage of the attention, GSpaA also reduces the sensitivity of patch size for patch-based methods. To effectively train S<sup>2</sup>AN when facing insufficient labeled data, a semisupervised strategy that combines supervised and unsupervised methods to augment labeled training data is proposed. Experiments on several HSI datasets in comparison to existing methods show the superiority of S<sup>2</sup>AN." @default.
- W4206550078 created "2022-01-25" @default.
- W4206550078 creator A5006614329 @default.
- W4206550078 creator A5038753313 @default.
- W4206550078 creator A5040618725 @default.
- W4206550078 creator A5048016442 @default.
- W4206550078 creator A5051767201 @default.
- W4206550078 creator A5071466474 @default.
- W4206550078 creator A5087319429 @default.
- W4206550078 creator A5091227928 @default.
- W4206550078 date "2022-01-01" @default.
- W4206550078 modified "2023-10-15" @default.
- W4206550078 title "A Spectral and Spatial Attention Network for Change Detection in Hyperspectral Images" @default.
- W4206550078 cites W1963659868 @default.
- W4206550078 cites W2039596145 @default.
- W4206550078 cites W2073134030 @default.
- W4206550078 cites W2085283969 @default.
- W4206550078 cites W2118116484 @default.
- W4206550078 cites W2129891925 @default.
- W4206550078 cites W2132222679 @default.
- W4206550078 cites W2134969826 @default.
- W4206550078 cites W2142789658 @default.
- W4206550078 cites W2163886442 @default.
- W4206550078 cites W2167799103 @default.
- W4206550078 cites W2194775991 @default.
- W4206550078 cites W2332183138 @default.
- W4206550078 cites W2531619007 @default.
- W4206550078 cites W2577809598 @default.
- W4206550078 cites W2587329506 @default.
- W4206550078 cites W2588117332 @default.
- W4206550078 cites W2782517596 @default.
- W4206550078 cites W2811044316 @default.
- W4206550078 cites W2890732922 @default.
- W4206550078 cites W2898923688 @default.
- W4206550078 cites W2900587135 @default.
- W4206550078 cites W2910587630 @default.
- W4206550078 cites W2911648799 @default.
- W4206550078 cites W2917189553 @default.
- W4206550078 cites W2953308875 @default.
- W4206550078 cites W2963037989 @default.
- W4206550078 cites W2963091558 @default.
- W4206550078 cites W2975135733 @default.
- W4206550078 cites W2979572910 @default.
- W4206550078 cites W2981266721 @default.
- W4206550078 cites W3003295287 @default.
- W4206550078 cites W3004423752 @default.
- W4206550078 cites W3009942016 @default.
- W4206550078 cites W3022397457 @default.
- W4206550078 cites W3027201985 @default.
- W4206550078 cites W3036453075 @default.
- W4206550078 cites W3037587714 @default.
- W4206550078 cites W3037640242 @default.
- W4206550078 cites W3038668823 @default.
- W4206550078 cites W3043257208 @default.
- W4206550078 cites W3048064159 @default.
- W4206550078 cites W3053564872 @default.
- W4206550078 cites W3081119210 @default.
- W4206550078 cites W3099102165 @default.
- W4206550078 cites W3099503507 @default.
- W4206550078 cites W3099831940 @default.
- W4206550078 cites W3105553032 @default.
- W4206550078 cites W3108948422 @default.
- W4206550078 cites W3119609454 @default.
- W4206550078 cites W3129277615 @default.
- W4206550078 cites W3134663792 @default.
- W4206550078 cites W3168588044 @default.
- W4206550078 cites W3179303890 @default.
- W4206550078 cites W639708223 @default.
- W4206550078 doi "https://doi.org/10.1109/tgrs.2021.3139077" @default.
- W4206550078 hasPublicationYear "2022" @default.
- W4206550078 type Work @default.
- W4206550078 citedByCount "14" @default.
- W4206550078 countsByYear W42065500782022 @default.
- W4206550078 countsByYear W42065500782023 @default.
- W4206550078 crossrefType "journal-article" @default.
- W4206550078 hasAuthorship W4206550078A5006614329 @default.
- W4206550078 hasAuthorship W4206550078A5038753313 @default.
- W4206550078 hasAuthorship W4206550078A5040618725 @default.
- W4206550078 hasAuthorship W4206550078A5048016442 @default.
- W4206550078 hasAuthorship W4206550078A5051767201 @default.
- W4206550078 hasAuthorship W4206550078A5071466474 @default.
- W4206550078 hasAuthorship W4206550078A5087319429 @default.
- W4206550078 hasAuthorship W4206550078A5091227928 @default.
- W4206550078 hasConcept C105795698 @default.
- W4206550078 hasConcept C121332964 @default.
- W4206550078 hasConcept C153180895 @default.
- W4206550078 hasConcept C154945302 @default.
- W4206550078 hasConcept C159078339 @default.
- W4206550078 hasConcept C159620131 @default.
- W4206550078 hasConcept C163716315 @default.
- W4206550078 hasConcept C33923547 @default.
- W4206550078 hasConcept C41008148 @default.
- W4206550078 hasConcept C62520636 @default.
- W4206550078 hasConcept C81363708 @default.
- W4206550078 hasConceptScore W4206550078C105795698 @default.
- W4206550078 hasConceptScore W4206550078C121332964 @default.
- W4206550078 hasConceptScore W4206550078C153180895 @default.
- W4206550078 hasConceptScore W4206550078C154945302 @default.