Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319303940> ?p ?o ?g. }
- W4319303940 endingPage "15" @default.
- W4319303940 startingPage "1" @default.
- W4319303940 abstract "Convolutional neural network (CNN)-based salient object detection (SOD) models have achieved promising performance in optical remote sensing images (ORSIs) in recent years. However, the restriction concerning the local sliding window operation of CNN has caused many existing CNN-based ORSI SOD models to still struggle with learning long-range relationships. To this end, a novel transformer framework is proposed for ORSI SOD, which is inspired by the powerful global dependency relationships of transformer networks. This is the first attempt to explore global and local details using transformer architecture for SOD in ORSIs. Concretely, we design an adaptive spatial tokenization transformer encoder to extract global–local features, which can accurately sparsify tokens for each input image and achieve competitive performance in ORSI SOD tasks. Then, a specific dense token aggregation decoder (DTAD) is proposed to generate saliency results, including three cascade decoders to integrate the global–local tokens and contextual dependencies. Extensive experiments indicate that the proposed model greatly surpasses 20 state-of-the-art (SOTA) SOD approaches on two standard ORSI SOD datasets under seven evaluation metrics. We also report comparison results to demonstrate the generalization capacity on the latest challenging ORSI datasets. In addition, we validate the contributions of different modules through a series of ablation analyses, especially the proposed adaptive spatial tokenization module (ASTM), which can halve the computational budget." @default.
- W4319303940 created "2023-02-07" @default.
- W4319303940 creator A5032271514 @default.
- W4319303940 creator A5040666380 @default.
- W4319303940 creator A5050147568 @default.
- W4319303940 creator A5070853337 @default.
- W4319303940 date "2023-01-01" @default.
- W4319303940 modified "2023-09-23" @default.
- W4319303940 title "Adaptive Spatial Tokenization Transformer for Salient Object Detection in Optical Remote Sensing Images" @default.
- W4319303940 cites W1974083340 @default.
- W4319303940 cites W2031489346 @default.
- W4319303940 cites W2047670868 @default.
- W4319303940 cites W2053506196 @default.
- W4319303940 cites W2070083314 @default.
- W4319303940 cites W2100470808 @default.
- W4319303940 cites W2160398355 @default.
- W4319303940 cites W2169632643 @default.
- W4319303940 cites W2194775991 @default.
- W4319303940 cites W2738676047 @default.
- W4319303940 cites W2744613561 @default.
- W4319303940 cites W2744876417 @default.
- W4319303940 cites W2791979332 @default.
- W4319303940 cites W2793668851 @default.
- W4319303940 cites W2800822850 @default.
- W4319303940 cites W2807746031 @default.
- W4319303940 cites W2888358068 @default.
- W4319303940 cites W2939217524 @default.
- W4319303940 cites W2944053494 @default.
- W4319303940 cites W2945874778 @default.
- W4319303940 cites W2963299740 @default.
- W4319303940 cites W2963529609 @default.
- W4319303940 cites W2963685207 @default.
- W4319303940 cites W2963706010 @default.
- W4319303940 cites W2963868681 @default.
- W4319303940 cites W2990984982 @default.
- W4319303940 cites W2997316506 @default.
- W4319303940 cites W3003121299 @default.
- W4319303940 cites W3025800305 @default.
- W4319303940 cites W3027763298 @default.
- W4319303940 cites W3029368604 @default.
- W4319303940 cites W3034684132 @default.
- W4319303940 cites W3035422681 @default.
- W4319303940 cites W3084740725 @default.
- W4319303940 cites W3091231798 @default.
- W4319303940 cites W3098389804 @default.
- W4319303940 cites W3102864715 @default.
- W4319303940 cites W3104979525 @default.
- W4319303940 cites W3108948422 @default.
- W4319303940 cites W3121523901 @default.
- W4319303940 cites W3129581972 @default.
- W4319303940 cites W3144925525 @default.
- W4319303940 cites W3166714471 @default.
- W4319303940 cites W3173446400 @default.
- W4319303940 cites W3179443972 @default.
- W4319303940 cites W3179565650 @default.
- W4319303940 cites W3203700770 @default.
- W4319303940 cites W3207668590 @default.
- W4319303940 cites W3208937872 @default.
- W4319303940 cites W3209011308 @default.
- W4319303940 cites W3210279979 @default.
- W4319303940 cites W3212645988 @default.
- W4319303940 cites W4206144626 @default.
- W4319303940 cites W4214561053 @default.
- W4319303940 cites W4220708493 @default.
- W4319303940 cites W4221014685 @default.
- W4319303940 cites W4221138999 @default.
- W4319303940 cites W4224330024 @default.
- W4319303940 cites W4225409070 @default.
- W4319303940 cites W4226537900 @default.
- W4319303940 cites W4239147634 @default.
- W4319303940 cites W4282938418 @default.
- W4319303940 cites W4283707199 @default.
- W4319303940 cites W4285295475 @default.
- W4319303940 cites W4288049158 @default.
- W4319303940 cites W4294691154 @default.
- W4319303940 cites W4312373555 @default.
- W4319303940 cites W4312572778 @default.
- W4319303940 cites W4313193709 @default.
- W4319303940 doi "https://doi.org/10.1109/tgrs.2023.3242987" @default.
- W4319303940 hasPublicationYear "2023" @default.
- W4319303940 type Work @default.
- W4319303940 citedByCount "1" @default.
- W4319303940 countsByYear W43193039402023 @default.
- W4319303940 crossrefType "journal-article" @default.
- W4319303940 hasAuthorship W4319303940A5032271514 @default.
- W4319303940 hasAuthorship W4319303940A5040666380 @default.
- W4319303940 hasAuthorship W4319303940A5050147568 @default.
- W4319303940 hasAuthorship W4319303940A5070853337 @default.
- W4319303940 hasConcept C111919701 @default.
- W4319303940 hasConcept C118505674 @default.
- W4319303940 hasConcept C119857082 @default.
- W4319303940 hasConcept C121332964 @default.
- W4319303940 hasConcept C153180895 @default.
- W4319303940 hasConcept C154945302 @default.
- W4319303940 hasConcept C165801399 @default.
- W4319303940 hasConcept C2776151529 @default.
- W4319303940 hasConcept C38652104 @default.
- W4319303940 hasConcept C41008148 @default.