Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386075500> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4386075500 abstract "This paper presents Scalable Semantic Transfer (SST), a novel training paradigm, to explore how to leverage the mutual benefits of the data from different label domains (i.e. various levels of label granularity) to train a powerful human parsing network. In practice, two common application scenarios are addressed, termed universal parsing and dedicated parsing, where the former aims to learn homogeneous human representations from multiple label domains and switch predictions by only using different segmentation heads, and the latter aims to learn a specific domain prediction while distilling the semantic knowledge from other domains. The proposed SST has the following appealing benefits: (1) it can capably serve as an effective training scheme to embed semantic associations of human body parts from multiple label domains into the human representation learning process; (2) it is an extensible semantic transfer framework without predetermining the overall relations of multiple label domains, which allows continuously adding human parsing datasets to promote the training. (3) the relevant modules are only used for auxiliary training and can be removed during inference, eliminating the extra reasoning cost. Experimental results demonstrate SST can effectively achieve promising universal human parsing performance as well as impressive improvements compared to its counterparts on three human parsing benchmarks (i.e., PASCAL-Person-Part, ATR, and CIHP). Code is available at https://github.com/yangjie-cv/SST." @default.
- W4386075500 created "2023-08-23" @default.
- W4386075500 creator A5003608795 @default.
- W4386075500 creator A5008549662 @default.
- W4386075500 creator A5010444377 @default.
- W4386075500 creator A5024438911 @default.
- W4386075500 creator A5054429473 @default.
- W4386075500 date "2023-06-01" @default.
- W4386075500 modified "2023-09-23" @default.
- W4386075500 title "Semantic Human Parsing via Scalable Semantic Transfer Over Multiple Label Domains" @default.
- W4386075500 cites W2104408738 @default.
- W4386075500 cites W2204578866 @default.
- W4386075500 cites W2519055561 @default.
- W4386075500 cites W2895818027 @default.
- W4386075500 cites W2963578952 @default.
- W4386075500 cites W2963758239 @default.
- W4386075500 cites W2963978393 @default.
- W4386075500 cites W2964072977 @default.
- W4386075500 cites W2964252655 @default.
- W4386075500 cites W2981750895 @default.
- W4386075500 cites W2981950698 @default.
- W4386075500 cites W2997973210 @default.
- W4386075500 cites W3009224666 @default.
- W4386075500 cites W3034760601 @default.
- W4386075500 cites W3034892601 @default.
- W4386075500 cites W3108326630 @default.
- W4386075500 cites W3108657013 @default.
- W4386075500 cites W3111653112 @default.
- W4386075500 cites W3138516171 @default.
- W4386075500 cites W3170343852 @default.
- W4386075500 cites W3204877997 @default.
- W4386075500 cites W4200631575 @default.
- W4386075500 cites W4221142658 @default.
- W4386075500 cites W4226030517 @default.
- W4386075500 cites W4312689172 @default.
- W4386075500 cites W4312815172 @default.
- W4386075500 doi "https://doi.org/10.1109/cvpr52729.2023.01861" @default.
- W4386075500 hasPublicationYear "2023" @default.
- W4386075500 type Work @default.
- W4386075500 citedByCount "0" @default.
- W4386075500 crossrefType "proceedings-article" @default.
- W4386075500 hasAuthorship W4386075500A5003608795 @default.
- W4386075500 hasAuthorship W4386075500A5008549662 @default.
- W4386075500 hasAuthorship W4386075500A5010444377 @default.
- W4386075500 hasAuthorship W4386075500A5024438911 @default.
- W4386075500 hasAuthorship W4386075500A5054429473 @default.
- W4386075500 hasConcept C119857082 @default.
- W4386075500 hasConcept C153083717 @default.
- W4386075500 hasConcept C154945302 @default.
- W4386075500 hasConcept C177774035 @default.
- W4386075500 hasConcept C186644900 @default.
- W4386075500 hasConcept C199360897 @default.
- W4386075500 hasConcept C204321447 @default.
- W4386075500 hasConcept C2776214188 @default.
- W4386075500 hasConcept C41008148 @default.
- W4386075500 hasConcept C48044578 @default.
- W4386075500 hasConcept C75608658 @default.
- W4386075500 hasConcept C77088390 @default.
- W4386075500 hasConceptScore W4386075500C119857082 @default.
- W4386075500 hasConceptScore W4386075500C153083717 @default.
- W4386075500 hasConceptScore W4386075500C154945302 @default.
- W4386075500 hasConceptScore W4386075500C177774035 @default.
- W4386075500 hasConceptScore W4386075500C186644900 @default.
- W4386075500 hasConceptScore W4386075500C199360897 @default.
- W4386075500 hasConceptScore W4386075500C204321447 @default.
- W4386075500 hasConceptScore W4386075500C2776214188 @default.
- W4386075500 hasConceptScore W4386075500C41008148 @default.
- W4386075500 hasConceptScore W4386075500C48044578 @default.
- W4386075500 hasConceptScore W4386075500C75608658 @default.
- W4386075500 hasConceptScore W4386075500C77088390 @default.
- W4386075500 hasLocation W43860755001 @default.
- W4386075500 hasOpenAccess W4386075500 @default.
- W4386075500 hasPrimaryLocation W43860755001 @default.
- W4386075500 hasRelatedWork W1590308178 @default.
- W4386075500 hasRelatedWork W1818857488 @default.
- W4386075500 hasRelatedWork W2167662847 @default.
- W4386075500 hasRelatedWork W2293457016 @default.
- W4386075500 hasRelatedWork W2369308426 @default.
- W4386075500 hasRelatedWork W2380023786 @default.
- W4386075500 hasRelatedWork W2502722637 @default.
- W4386075500 hasRelatedWork W2789919619 @default.
- W4386075500 hasRelatedWork W2977842567 @default.
- W4386075500 hasRelatedWork W1551406738 @default.
- W4386075500 isParatext "false" @default.
- W4386075500 isRetracted "false" @default.
- W4386075500 workType "article" @default.