Matches in SemOpenAlex for { <https://semopenalex.org/work/W3174523984> ?p ?o ?g. }
- W3174523984 abstract "Camouflaged object detection (COD) aims to segment camouflaged objects hiding in the environment, which is challenging due to the similar appearance of camouflaged objects and their surroundings. Research in biology suggests that depth can provide useful object localization cues for camouflaged object discovery, as all the animals have 3D perception ability. However, the depth information has not been exploited for camouflaged object detection. To explore the contribution of depth for camouflage detection, we present a depth-guided camouflaged object detection network with pre-computed depth maps from existing monocular depth estimation methods. Due to the domain gap between the depth estimation dataset and our camouflaged object detection dataset, the generated depth may not be accurate enough to be directly used in our framework. We then introduce a depth quality assessment module to evaluate the quality of depth based on the model prediction from both RGB COD branch and RGB-D COD branch. During training, only high-quality depth is used to update the modal interaction module for multi-modal learning. During testing, our depth quality assessment module can effectively determine the contribution of depth and select the RGB branch or RGB-D branch for camouflage prediction. Extensive experiments on various camouflaged object detection datasets prove the effectiveness of our solution in exploring the depth information for camouflaged object detection. Our code and data is publicly available at: url{this https URL}." @default.
- W3174523984 created "2021-07-05" @default.
- W3174523984 creator A5021094497 @default.
- W3174523984 creator A5021390512 @default.
- W3174523984 creator A5032741887 @default.
- W3174523984 creator A5036202579 @default.
- W3174523984 creator A5054874551 @default.
- W3174523984 creator A5066621365 @default.
- W3174523984 date "2021-06-24" @default.
- W3174523984 modified "2023-09-25" @default.
- W3174523984 title "Depth-Guided Camouflaged Object Detection." @default.
- W3174523984 cites W1168547848 @default.
- W3174523984 cites W1534477342 @default.
- W3174523984 cites W1687112550 @default.
- W3174523984 cites W1901129140 @default.
- W3174523984 cites W1903029394 @default.
- W3174523984 cites W1938386764 @default.
- W3174523984 cites W1966025376 @default.
- W3174523984 cites W1968773971 @default.
- W3174523984 cites W1985290912 @default.
- W3174523984 cites W1993713494 @default.
- W3174523984 cites W2022508996 @default.
- W3174523984 cites W2038754339 @default.
- W3174523984 cites W2039298799 @default.
- W3174523984 cites W2063779601 @default.
- W3174523984 cites W2066813062 @default.
- W3174523984 cites W2067912884 @default.
- W3174523984 cites W20683899 @default.
- W3174523984 cites W2085411191 @default.
- W3174523984 cites W2139088960 @default.
- W3174523984 cites W2194775991 @default.
- W3174523984 cites W2221101993 @default.
- W3174523984 cites W2412782625 @default.
- W3174523984 cites W2461758788 @default.
- W3174523984 cites W2597742770 @default.
- W3174523984 cites W2600383743 @default.
- W3174523984 cites W2628983296 @default.
- W3174523984 cites W2775906317 @default.
- W3174523984 cites W2777686015 @default.
- W3174523984 cites W2796975587 @default.
- W3174523984 cites W2798857366 @default.
- W3174523984 cites W2800623305 @default.
- W3174523984 cites W2866634454 @default.
- W3174523984 cites W2899770794 @default.
- W3174523984 cites W2911415584 @default.
- W3174523984 cites W2939217524 @default.
- W3174523984 cites W2942368658 @default.
- W3174523984 cites W2943545929 @default.
- W3174523984 cites W2945469194 @default.
- W3174523984 cites W2957414648 @default.
- W3174523984 cites W2962864875 @default.
- W3174523984 cites W2962948774 @default.
- W3174523984 cites W2963037989 @default.
- W3174523984 cites W2963112696 @default.
- W3174523984 cites W2963150697 @default.
- W3174523984 cites W2963238274 @default.
- W3174523984 cites W2963399829 @default.
- W3174523984 cites W2963529609 @default.
- W3174523984 cites W2963868681 @default.
- W3174523984 cites W2964059111 @default.
- W3174523984 cites W2971014764 @default.
- W3174523984 cites W2987701848 @default.
- W3174523984 cites W2990984982 @default.
- W3174523984 cites W2998449272 @default.
- W3174523984 cites W3002301267 @default.
- W3174523984 cites W3003121299 @default.
- W3174523984 cites W3009702330 @default.
- W3174523984 cites W3034320133 @default.
- W3174523984 cites W3035146082 @default.
- W3174523984 cites W3035284915 @default.
- W3174523984 cites W3035290198 @default.
- W3174523984 cites W3035633116 @default.
- W3174523984 cites W3035687312 @default.
- W3174523984 cites W3044273045 @default.
- W3174523984 cites W3081167590 @default.
- W3174523984 cites W3092344722 @default.
- W3174523984 cites W3097053213 @default.
- W3174523984 cites W3109623941 @default.
- W3174523984 cites W3118595994 @default.
- W3174523984 cites W3118710621 @default.
- W3174523984 cites W3119780109 @default.
- W3174523984 cites W3176152216 @default.
- W3174523984 cites W933200379 @default.
- W3174523984 hasPublicationYear "2021" @default.
- W3174523984 type Work @default.
- W3174523984 sameAs 3174523984 @default.
- W3174523984 citedByCount "0" @default.
- W3174523984 crossrefType "posted-content" @default.
- W3174523984 hasAuthorship W3174523984A5021094497 @default.
- W3174523984 hasAuthorship W3174523984A5021390512 @default.
- W3174523984 hasAuthorship W3174523984A5032741887 @default.
- W3174523984 hasAuthorship W3174523984A5036202579 @default.
- W3174523984 hasAuthorship W3174523984A5054874551 @default.
- W3174523984 hasAuthorship W3174523984A5066621365 @default.
- W3174523984 hasConcept C108583219 @default.
- W3174523984 hasConcept C111472728 @default.
- W3174523984 hasConcept C115961682 @default.
- W3174523984 hasConcept C134306372 @default.
- W3174523984 hasConcept C138885662 @default.
- W3174523984 hasConcept C141268832 @default.