FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312257162> ?p ?o ?g. }

• W4312257162 endingPage "387" @default.
• W4312257162 startingPage "369" @default.
• W4312257162 abstract "Unsupervised domain adaptation in semantic segmentation alleviates the reliance on expensive pixel-wise annotation. It uses a labeled source domain dataset as well as unlabeled target domain images to learn a segmentation network. In this paper, we observe two main issues of existing domain-invariant learning framework. (1) Being distracted by the feature distribution alignment, the network cannot focus on the segmentation task. (2) Fitting source domain data well would compromise the target domain performance. To address these issues, we propose DecoupleNet to alleviate source domain overfitting and let the final model focus more on the segmentation task. Also, we put forward Self-Discrimination (SD) and introduce an auxiliary classifier to learn more discriminative target domain features with pseudo labels. Finally, we propose Online Enhanced Self-Training (OEST) to contextually enhance the quality of pseudo labels in an online manner. Experiments show our method outperforms existing state-of-the-art methods. Extensive ablation studies verify the effectiveness of each component. Code is available at https://github.com/dvlab-research/DecoupleNet ." @default.
• W4312257162 created "2023-01-04" @default.
• W4312257162 creator A5024489046 @default.
• W4312257162 creator A5032067104 @default.
• W4312257162 creator A5033446531 @default.
• W4312257162 creator A5038086218 @default.
• W4312257162 creator A5047344339 @default.
• W4312257162 creator A5064499660 @default.
• W4312257162 creator A5066983698 @default.
• W4312257162 creator A5078109015 @default.
• W4312257162 date "2022-01-01" @default.
• W4312257162 modified "2023-09-30" @default.
• W4312257162 title "DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation" @default.
• W4312257162 cites W1745334888 @default.
• W4312257162 cites W1901129140 @default.
• W4312257162 cites W2031342017 @default.
• W4312257162 cites W2128053425 @default.
• W4312257162 cites W2194775991 @default.
• W4312257162 cites W2340897893 @default.
• W4312257162 cites W2395611524 @default.
• W4312257162 cites W2412782625 @default.
• W4312257162 cites W2431874326 @default.
• W4312257162 cites W2487365028 @default.
• W4312257162 cites W2560023338 @default.
• W4312257162 cites W2593414223 @default.
• W4312257162 cites W2593768305 @default.
• W4312257162 cites W2798964604 @default.
• W4312257162 cites W2799213142 @default.
• W4312257162 cites W2895281799 @default.
• W4312257162 cites W2895340641 @default.
• W4312257162 cites W2948959975 @default.
• W4312257162 cites W2954628187 @default.
• W4312257162 cites W2955058313 @default.
• W4312257162 cites W2963073217 @default.
• W4312257162 cites W2963107255 @default.
• W4312257162 cites W2963120918 @default.
• W4312257162 cites W2963240485 @default.
• W4312257162 cites W2963789515 @default.
• W4312257162 cites W2963864946 @default.
• W4312257162 cites W2963870446 @default.
• W4312257162 cites W2963881378 @default.
• W4312257162 cites W2964055354 @default.
• W4312257162 cites W2964057616 @default.
• W4312257162 cites W2964217532 @default.
• W4312257162 cites W2964288524 @default.
• W4312257162 cites W2969893028 @default.
• W4312257162 cites W2972285644 @default.
• W4312257162 cites W2979920800 @default.
• W4312257162 cites W2981392058 @default.
• W4312257162 cites W2981429991 @default.
• W4312257162 cites W2981630749 @default.
• W4312257162 cites W2981689412 @default.
• W4312257162 cites W2981899103 @default.
• W4312257162 cites W2982259084 @default.
• W4312257162 cites W2986831462 @default.
• W4312257162 cites W2991405316 @default.
• W4312257162 cites W2997310315 @default.
• W4312257162 cites W2998607115 @default.
• W4312257162 cites W3034591020 @default.
• W4312257162 cites W3035236545 @default.
• W4312257162 cites W3035294798 @default.
• W4312257162 cites W3107502112 @default.
• W4312257162 cites W3107909383 @default.
• W4312257162 cites W3108125093 @default.
• W4312257162 cites W3108400054 @default.
• W4312257162 cites W3108560336 @default.
• W4312257162 cites W3108566666 @default.
• W4312257162 cites W3110486195 @default.
• W4312257162 cites W3165246274 @default.
• W4312257162 cites W3172949220 @default.
• W4312257162 cites W3175294391 @default.
• W4312257162 cites W3175481246 @default.
• W4312257162 cites W3180003570 @default.
• W4312257162 cites W3183988645 @default.
• W4312257162 cites W3187663758 @default.
• W4312257162 cites W3188258165 @default.
• W4312257162 cites W3202422321 @default.
• W4312257162 cites W3202959559 @default.
• W4312257162 cites W4214623175 @default.
• W4312257162 cites W4229723800 @default.
• W4312257162 cites W4230194115 @default.
• W4312257162 doi "https://doi.org/10.1007/978-3-031-19827-4_22" @default.
• W4312257162 hasPublicationYear "2022" @default.
• W4312257162 type Work @default.
• W4312257162 citedByCount "9" @default.
• W4312257162 countsByYear W43122571622023 @default.
• W4312257162 crossrefType "book-chapter" @default.
• W4312257162 hasAuthorship W4312257162A5024489046 @default.
• W4312257162 hasAuthorship W4312257162A5032067104 @default.
• W4312257162 hasAuthorship W4312257162A5033446531 @default.
• W4312257162 hasAuthorship W4312257162A5038086218 @default.
• W4312257162 hasAuthorship W4312257162A5047344339 @default.
• W4312257162 hasAuthorship W4312257162A5064499660 @default.
• W4312257162 hasAuthorship W4312257162A5066983698 @default.
• W4312257162 hasAuthorship W4312257162A5078109015 @default.
• W4312257162 hasBestOaLocation W43122571622 @default.
• W4312257162 hasConcept C111919701 @default.
• W4312257162 hasConcept C119857082 @default.

• next