FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3122052861> ?p ?o ?g. }

• W3122052861 abstract "Self-training is a competitive approach in domain adaptive segmentation, which trains the network with the pseudo labels on the target domain. However inevitably, the pseudo labels are noisy and the target features are dispersed due to the discrepancy between source and target domains. In this paper, we rely on representative prototypes, the feature centroids of classes, to address the two issues for unsupervised domain adaptation. In particular, we take one step further and exploit the feature distances from prototypes that provide richer information than mere prototypes. Specifically, we use it to estimate the likelihood of pseudo labels to facilitate online correction in the course of training. Meanwhile, we align the prototypical assignments based on relative feature distances for two different views of the same target, producing a more compact target feature space. Moreover, we find that distilling the already learned knowledge to a self-supervised pretrained model further boosts the performance. Our method shows tremendous performance advantage over state-of-the-art methods. We will make the code publicly available." @default.
• W3122052861 created "2021-02-01" @default.
• W3122052861 creator A5001330715 @default.
• W3122052861 creator A5011877804 @default.
• W3122052861 creator A5018967320 @default.
• W3122052861 creator A5066102428 @default.
• W3122052861 creator A5070617771 @default.
• W3122052861 creator A5088174174 @default.
• W3122052861 date "2021-01-26" @default.
• W3122052861 modified "2023-09-27" @default.
• W3122052861 title "Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation" @default.
• W3122052861 cites W1821462560 @default.
• W3122052861 cites W2099471712 @default.
• W3122052861 cites W2104094955 @default.
• W3122052861 cites W2159291411 @default.
• W3122052861 cites W2194775991 @default.
• W3122052861 cites W2308529009 @default.
• W3122052861 cites W2340897893 @default.
• W3122052861 cites W2412782625 @default.
• W3122052861 cites W2431874326 @default.
• W3122052861 cites W2487365028 @default.
• W3122052861 cites W2558661413 @default.
• W3122052861 cites W2592335154 @default.
• W3122052861 cites W2601450892 @default.
• W3122052861 cites W2746314669 @default.
• W3122052861 cites W2786672974 @default.
• W3122052861 cites W2795889831 @default.
• W3122052861 cites W2796346823 @default.
• W3122052861 cites W2798964604 @default.
• W3122052861 cites W2798991696 @default.
• W3122052861 cites W2883725317 @default.
• W3122052861 cites W2890336707 @default.
• W3122052861 cites W2895281799 @default.
• W3122052861 cites W2932414082 @default.
• W3122052861 cites W2945007112 @default.
• W3122052861 cites W2950635901 @default.
• W3122052861 cites W2951357534 @default.
• W3122052861 cites W2962687275 @default.
• W3122052861 cites W2962742544 @default.
• W3122052861 cites W2962762068 @default.
• W3122052861 cites W2962808524 @default.
• W3122052861 cites W2963073217 @default.
• W3122052861 cites W2963107255 @default.
• W3122052861 cites W2963240485 @default.
• W3122052861 cites W2963759070 @default.
• W3122052861 cites W2963789515 @default.
• W3122052861 cites W2963800509 @default.
• W3122052861 cites W2963956526 @default.
• W3122052861 cites W2964126011 @default.
• W3122052861 cites W2969893028 @default.
• W3122052861 cites W2970092410 @default.
• W3122052861 cites W2970241862 @default.
• W3122052861 cites W2972285644 @default.
• W3122052861 cites W2975758481 @default.
• W3122052861 cites W2978625989 @default.
• W3122052861 cites W2980096013 @default.
• W3122052861 cites W2981392058 @default.
• W3122052861 cites W2981429991 @default.
• W3122052861 cites W2981512393 @default.
• W3122052861 cites W2981873476 @default.
• W3122052861 cites W2981925632 @default.
• W3122052861 cites W2986381065 @default.
• W3122052861 cites W2986405467 @default.
• W3122052861 cites W2998607115 @default.
• W3122052861 cites W3005680577 @default.
• W3122052861 cites W3009033475 @default.
• W3122052861 cites W3009979396 @default.
• W3122052861 cites W3030206225 @default.
• W3122052861 cites W3033053533 @default.
• W3122052861 cites W3034247804 @default.
• W3122052861 cites W3034781633 @default.
• W3122052861 cites W3035002246 @default.
• W3122052861 cites W3035060554 @default.
• W3122052861 cites W3035160371 @default.
• W3122052861 cites W3035524453 @default.
• W3122052861 cites W3036224891 @default.
• W3122052861 cites W3036982689 @default.
• W3122052861 cites W3042609801 @default.
• W3122052861 cites W3091812030 @default.
• W3122052861 cites W3093222659 @default.
• W3122052861 cites W3102631365 @default.
• W3122052861 cites W3108560336 @default.
• W3122052861 doi "https://doi.org/10.48550/arxiv.2101.10979" @default.
• W3122052861 hasPublicationYear "2021" @default.
• W3122052861 type Work @default.
• W3122052861 sameAs 3122052861 @default.
• W3122052861 citedByCount "13" @default.
• W3122052861 countsByYear W31220528612021 @default.
• W3122052861 crossrefType "posted-content" @default.
• W3122052861 hasAuthorship W3122052861A5001330715 @default.
• W3122052861 hasAuthorship W3122052861A5011877804 @default.
• W3122052861 hasAuthorship W3122052861A5018967320 @default.
• W3122052861 hasAuthorship W3122052861A5066102428 @default.
• W3122052861 hasAuthorship W3122052861A5070617771 @default.
• W3122052861 hasAuthorship W3122052861A5088174174 @default.
• W3122052861 hasBestOaLocation W31220528611 @default.
• W3122052861 hasConcept C119857082 @default.
• W3122052861 hasConcept C120665830 @default.
• W3122052861 hasConcept C121332964 @default.
• W3122052861 hasConcept C134306372 @default.

• next