Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285243313> ?p ?o ?g. }
- W4285243313 endingPage "11" @default.
- W4285243313 startingPage "1" @default.
- W4285243313 abstract "Deep learning has substantially pushed forward remote sensing image change detection through extracting discriminative hierarchical features. However, as the increasingly high resolution remote sensing images have abundant spatial details but limited spectral information, the use of conventional backbone networks would give rise to blurry boundaries between different semantics among hierarchical features. This explains why most false alarms in the final predictions distribute around change boundaries. To alleviate the problem, we pay attention to feature refinement and propose deep learning networks that deliver improved separability (ISNet). Our ISNet reaps the advantages from two strategies applied to refining bi-temporal feature hierarchies: (i) margin maximization that clarifies the gap between changed and unchanged semantics, and (ii) targeted arrangement of attention mechanisms that directs the use of channel attention and spatial attention for highlighting semantic and positional information, respectively. Specifically, we insert channel attention modules into share-weighted backbone networks to facilitate semantic-specific feature extraction. The semantic boundaries in the extracted bi-temporal hierarchical features are then clarified by margin maximization modules, followed by spatial attention modules to enhance positional change responses. A top-down fusion pathway makes the final refined features cover multi-scale representations and have strong separability for remote sensing image change detection. Extensive experimental evaluations demonstrate that our ISNet achieves state-of-the-art performance on the LEVIR-CD, SYSU-CD, and Season-Varying datasets, in terms of Overall Accuracy (OA), Intersection-of-Union (IoU), and F1 score. Code is available at https://github.com/xingronaldo/ISNet." @default.
- W4285243313 created "2022-07-14" @default.
- W4285243313 creator A5012529382 @default.
- W4285243313 creator A5060722723 @default.
- W4285243313 creator A5080476856 @default.
- W4285243313 date "2022-01-01" @default.
- W4285243313 modified "2023-10-16" @default.
- W4285243313 title "ISNet: Towards Improving Separability for Remote Sensing Image Change Detection" @default.
- W4285243313 cites W1669730594 @default.
- W4285243313 cites W2085289201 @default.
- W4285243313 cites W2157026765 @default.
- W4285243313 cites W2194775991 @default.
- W4285243313 cites W2410883106 @default.
- W4285243313 cites W2476548250 @default.
- W4285243313 cites W2518815253 @default.
- W4285243313 cites W2549139847 @default.
- W4285243313 cites W2565639579 @default.
- W4285243313 cites W2601564443 @default.
- W4285243313 cites W2740982616 @default.
- W4285243313 cites W2752782242 @default.
- W4285243313 cites W2783165089 @default.
- W4285243313 cites W2805152403 @default.
- W4285243313 cites W2888493720 @default.
- W4285243313 cites W2919115771 @default.
- W4285243313 cites W2949343319 @default.
- W4285243313 cites W2953308875 @default.
- W4285243313 cites W2955058313 @default.
- W4285243313 cites W2962914239 @default.
- W4285243313 cites W2963800363 @default.
- W4285243313 cites W2964137095 @default.
- W4285243313 cites W2969081030 @default.
- W4285243313 cites W2990827756 @default.
- W4285243313 cites W3026446890 @default.
- W4285243313 cites W3034552520 @default.
- W4285243313 cites W3036453075 @default.
- W4285243313 cites W3095567726 @default.
- W4285243313 cites W3097947628 @default.
- W4285243313 cites W3099503507 @default.
- W4285243313 cites W3123813572 @default.
- W4285243313 cites W3130754787 @default.
- W4285243313 cites W3133726918 @default.
- W4285243313 cites W3142421496 @default.
- W4285243313 cites W3144332889 @default.
- W4285243313 cites W3146366485 @default.
- W4285243313 cites W3157062364 @default.
- W4285243313 cites W3160330105 @default.
- W4285243313 cites W3163207600 @default.
- W4285243313 cites W3175672129 @default.
- W4285243313 cites W3176330035 @default.
- W4285243313 cites W3177155650 @default.
- W4285243313 cites W3178882511 @default.
- W4285243313 cites W3179888767 @default.
- W4285243313 cites W3182928821 @default.
- W4285243313 cites W3186032668 @default.
- W4285243313 cites W3187748454 @default.
- W4285243313 cites W3196107618 @default.
- W4285243313 cites W3210579416 @default.
- W4285243313 cites W3214719104 @default.
- W4285243313 cites W4214588794 @default.
- W4285243313 doi "https://doi.org/10.1109/tgrs.2022.3174276" @default.
- W4285243313 hasPublicationYear "2022" @default.
- W4285243313 type Work @default.
- W4285243313 citedByCount "22" @default.
- W4285243313 countsByYear W42852433132022 @default.
- W4285243313 countsByYear W42852433132023 @default.
- W4285243313 crossrefType "journal-article" @default.
- W4285243313 hasAuthorship W4285243313A5012529382 @default.
- W4285243313 hasAuthorship W4285243313A5060722723 @default.
- W4285243313 hasAuthorship W4285243313A5080476856 @default.
- W4285243313 hasConcept C119857082 @default.
- W4285243313 hasConcept C127162648 @default.
- W4285243313 hasConcept C127313418 @default.
- W4285243313 hasConcept C127413603 @default.
- W4285243313 hasConcept C138885662 @default.
- W4285243313 hasConcept C146978453 @default.
- W4285243313 hasConcept C153180895 @default.
- W4285243313 hasConcept C154945302 @default.
- W4285243313 hasConcept C162324750 @default.
- W4285243313 hasConcept C175444787 @default.
- W4285243313 hasConcept C184337299 @default.
- W4285243313 hasConcept C199360897 @default.
- W4285243313 hasConcept C203595873 @default.
- W4285243313 hasConcept C2776330181 @default.
- W4285243313 hasConcept C2776401178 @default.
- W4285243313 hasConcept C31258907 @default.
- W4285243313 hasConcept C41008148 @default.
- W4285243313 hasConcept C41895202 @default.
- W4285243313 hasConcept C52622490 @default.
- W4285243313 hasConcept C59404180 @default.
- W4285243313 hasConcept C62649853 @default.
- W4285243313 hasConcept C64543145 @default.
- W4285243313 hasConcept C774472 @default.
- W4285243313 hasConcept C97931131 @default.
- W4285243313 hasConceptScore W4285243313C119857082 @default.
- W4285243313 hasConceptScore W4285243313C127162648 @default.
- W4285243313 hasConceptScore W4285243313C127313418 @default.
- W4285243313 hasConceptScore W4285243313C127413603 @default.
- W4285243313 hasConceptScore W4285243313C138885662 @default.