Matches in SemOpenAlex for { <https://semopenalex.org/work/W4365420797> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4365420797 endingPage "308" @default.
- W4365420797 startingPage "296" @default.
- W4365420797 abstract "Unsupervised domain adaptation(UDA) has been applied to image semantic segmentation to solve the problem of domain offset. However, in some difficult categories with poor recognition accuracy, the segmentation effects are still not ideal. To this end, in this paper, Intra-subdomain adaptation adversarial learning segmentation method based on Dynamic Pseudo Labels(IDPL) is proposed. The whole process consists of 3 steps: Firstly, the instance-level pseudo label dynamic generation module is proposed, which fuses the class matching information in global classes and local instances, thus adaptively generating the optimal threshold for each class, obtaining high-quality pseudo labels. Secondly, the subdomain classifier module based on instance confidence is constructed, which can dynamically divide the target domain into easy and difficult subdomains according to the relative proportion of easy and difficult instances. Finally, the subdomain adversarial learning module based on self-attention is proposed. It uses multi-head self-attention to confront the easy and difficult subdomains at the class level with the help of generated high-quality pseudo labels, so as to focus on mining the features of difficult categories in the high-entropy region of target domain images, which promotes class-level conditional distribution alignment between the subdomains, improving the segmentation performance of difficult categories. For the difficult categories, the experimental results show that the performance of IDPL is significantly improved compared with other latest mainstream methods." @default.
- W4365420797 created "2023-04-14" @default.
- W4365420797 creator A5019751431 @default.
- W4365420797 creator A5032282299 @default.
- W4365420797 creator A5054284760 @default.
- W4365420797 creator A5054925527 @default.
- W4365420797 creator A5069354293 @default.
- W4365420797 date "2023-01-01" @default.
- W4365420797 modified "2023-09-27" @default.
- W4365420797 title "IDPL: Intra-subdomain Adaptation Adversarial Learning Segmentation Method Based on Dynamic Pseudo Labels" @default.
- W4365420797 cites W2194775991 @default.
- W4365420797 cites W2340897893 @default.
- W4365420797 cites W2412782625 @default.
- W4365420797 cites W2431874326 @default.
- W4365420797 cites W2487365028 @default.
- W4365420797 cites W2895281799 @default.
- W4365420797 cites W2963073217 @default.
- W4365420797 cites W2963107255 @default.
- W4365420797 cites W2981624307 @default.
- W4365420797 cites W2985406498 @default.
- W4365420797 cites W3034247804 @default.
- W4365420797 cites W3034562924 @default.
- W4365420797 cites W3035294798 @default.
- W4365420797 cites W3119635706 @default.
- W4365420797 cites W3170700905 @default.
- W4365420797 cites W3172243934 @default.
- W4365420797 cites W3173206925 @default.
- W4365420797 cites W4287124998 @default.
- W4365420797 cites W4312815761 @default.
- W4365420797 doi "https://doi.org/10.1007/978-3-031-30105-6_25" @default.
- W4365420797 hasPublicationYear "2023" @default.
- W4365420797 type Work @default.
- W4365420797 citedByCount "0" @default.
- W4365420797 crossrefType "book-chapter" @default.
- W4365420797 hasAuthorship W4365420797A5019751431 @default.
- W4365420797 hasAuthorship W4365420797A5032282299 @default.
- W4365420797 hasAuthorship W4365420797A5054284760 @default.
- W4365420797 hasAuthorship W4365420797A5054925527 @default.
- W4365420797 hasAuthorship W4365420797A5069354293 @default.
- W4365420797 hasBestOaLocation W43654207972 @default.
- W4365420797 hasConcept C119857082 @default.
- W4365420797 hasConcept C153180895 @default.
- W4365420797 hasConcept C154945302 @default.
- W4365420797 hasConcept C37736160 @default.
- W4365420797 hasConcept C41008148 @default.
- W4365420797 hasConcept C89600930 @default.
- W4365420797 hasConcept C95623464 @default.
- W4365420797 hasConceptScore W4365420797C119857082 @default.
- W4365420797 hasConceptScore W4365420797C153180895 @default.
- W4365420797 hasConceptScore W4365420797C154945302 @default.
- W4365420797 hasConceptScore W4365420797C37736160 @default.
- W4365420797 hasConceptScore W4365420797C41008148 @default.
- W4365420797 hasConceptScore W4365420797C89600930 @default.
- W4365420797 hasConceptScore W4365420797C95623464 @default.
- W4365420797 hasLocation W43654207971 @default.
- W4365420797 hasLocation W43654207972 @default.
- W4365420797 hasOpenAccess W4365420797 @default.
- W4365420797 hasPrimaryLocation W43654207971 @default.
- W4365420797 hasRelatedWork W2460937040 @default.
- W4365420797 hasRelatedWork W2921036759 @default.
- W4365420797 hasRelatedWork W2961085424 @default.
- W4365420797 hasRelatedWork W3017503936 @default.
- W4365420797 hasRelatedWork W3205128835 @default.
- W4365420797 hasRelatedWork W4206076898 @default.
- W4365420797 hasRelatedWork W4286899967 @default.
- W4365420797 hasRelatedWork W4300511536 @default.
- W4365420797 hasRelatedWork W4379255972 @default.
- W4365420797 hasRelatedWork W3158004940 @default.
- W4365420797 isParatext "false" @default.
- W4365420797 isRetracted "false" @default.
- W4365420797 workType "book-chapter" @default.