Matches in SemOpenAlex for { <https://semopenalex.org/work/W3162187798> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W3162187798 abstract "Recent works show that mean-teaching is an effective framework for unsupervised domain adaptive person re-identification. However, existing methods perform contrastive learning on selected samples between teacher and student networks, which is sensitive to noises in pseudo labels and neglects the relationship among most samples. Moreover, these methods are not effective in cooperation of different teacher networks. To handle these issues, this paper proposes a Graph Consistency based Mean-Teaching (GCMT) method with constructing the Graph Consistency Constraint (GCC) between teacher and student networks. Specifically, given unlabeled training images, we apply teacher networks to extract corresponding features and further construct a teacher graph for each teacher network to describe the similarity relationships among training images. To boost the representation learning, different teacher graphs are fused to provide the supervise signal for optimizing student networks. GCMT fuses similarity relationships predicted by different teacher networks as supervision and effectively optimizes student networks with more sample relationships involved. Experiments on three datasets, i.e., Market-1501, DukeMTMCreID, and MSMT17, show that proposed GCMT outperforms state-of-the-art methods by clear margin. Specially, GCMT even outperforms the previous method that uses a deeper backbone. Experimental results also show that GCMT can effectively boost the performance with multiple teacher and student networks. Our code is available at https://github.com/liu-xb/GCMT ." @default.
- W3162187798 created "2021-05-24" @default.
- W3162187798 creator A5055433405 @default.
- W3162187798 creator A5081417229 @default.
- W3162187798 date "2021-05-11" @default.
- W3162187798 modified "2023-09-26" @default.
- W3162187798 title "Graph Consistency Based Mean-Teaching for Unsupervised Domain Adaptive Person Re-Identification" @default.
- W3162187798 cites W1982925187 @default.
- W3162187798 cites W2108598243 @default.
- W3162187798 cites W2194775991 @default.
- W3162187798 cites W2204750386 @default.
- W3162187798 cites W2585635281 @default.
- W3162187798 cites W2592691248 @default.
- W3162187798 cites W2738760914 @default.
- W3162187798 cites W2885476150 @default.
- W3162187798 cites W2890155761 @default.
- W3162187798 cites W2904427185 @default.
- W3162187798 cites W2953214814 @default.
- W3162187798 cites W2957037461 @default.
- W3162187798 cites W2957279468 @default.
- W3162187798 cites W2962859295 @default.
- W3162187798 cites W2963047834 @default.
- W3162187798 cites W2963438548 @default.
- W3162187798 cites W2963446712 @default.
- W3162187798 cites W2963735582 @default.
- W3162187798 cites W2964344300 @default.
- W3162187798 cites W2988852559 @default.
- W3162187798 cites W2995852213 @default.
- W3162187798 cites W2998508940 @default.
- W3162187798 cites W3034580371 @default.
- W3162187798 cites W3092883857 @default.
- W3162187798 cites W3103165805 @default.
- W3162187798 cites W3106772544 @default.
- W3162187798 cites W3106858249 @default.
- W3162187798 cites W3135942694 @default.
- W3162187798 doi "https://doi.org/10.48550/arxiv.2105.04776" @default.
- W3162187798 hasPublicationYear "2021" @default.
- W3162187798 type Work @default.
- W3162187798 sameAs 3162187798 @default.
- W3162187798 citedByCount "0" @default.
- W3162187798 crossrefType "posted-content" @default.
- W3162187798 hasAuthorship W3162187798A5055433405 @default.
- W3162187798 hasAuthorship W3162187798A5081417229 @default.
- W3162187798 hasBestOaLocation W31621877981 @default.
- W3162187798 hasConcept C103278499 @default.
- W3162187798 hasConcept C115961682 @default.
- W3162187798 hasConcept C116834253 @default.
- W3162187798 hasConcept C119857082 @default.
- W3162187798 hasConcept C132525143 @default.
- W3162187798 hasConcept C153180895 @default.
- W3162187798 hasConcept C154945302 @default.
- W3162187798 hasConcept C177264268 @default.
- W3162187798 hasConcept C199360897 @default.
- W3162187798 hasConcept C2524010 @default.
- W3162187798 hasConcept C2776036281 @default.
- W3162187798 hasConcept C2776436953 @default.
- W3162187798 hasConcept C2776760102 @default.
- W3162187798 hasConcept C33923547 @default.
- W3162187798 hasConcept C41008148 @default.
- W3162187798 hasConcept C59822182 @default.
- W3162187798 hasConcept C774472 @default.
- W3162187798 hasConcept C80444323 @default.
- W3162187798 hasConcept C86803240 @default.
- W3162187798 hasConceptScore W3162187798C103278499 @default.
- W3162187798 hasConceptScore W3162187798C115961682 @default.
- W3162187798 hasConceptScore W3162187798C116834253 @default.
- W3162187798 hasConceptScore W3162187798C119857082 @default.
- W3162187798 hasConceptScore W3162187798C132525143 @default.
- W3162187798 hasConceptScore W3162187798C153180895 @default.
- W3162187798 hasConceptScore W3162187798C154945302 @default.
- W3162187798 hasConceptScore W3162187798C177264268 @default.
- W3162187798 hasConceptScore W3162187798C199360897 @default.
- W3162187798 hasConceptScore W3162187798C2524010 @default.
- W3162187798 hasConceptScore W3162187798C2776036281 @default.
- W3162187798 hasConceptScore W3162187798C2776436953 @default.
- W3162187798 hasConceptScore W3162187798C2776760102 @default.
- W3162187798 hasConceptScore W3162187798C33923547 @default.
- W3162187798 hasConceptScore W3162187798C41008148 @default.
- W3162187798 hasConceptScore W3162187798C59822182 @default.
- W3162187798 hasConceptScore W3162187798C774472 @default.
- W3162187798 hasConceptScore W3162187798C80444323 @default.
- W3162187798 hasConceptScore W3162187798C86803240 @default.
- W3162187798 hasLocation W31621877981 @default.
- W3162187798 hasOpenAccess W3162187798 @default.
- W3162187798 hasPrimaryLocation W31621877981 @default.
- W3162187798 hasRelatedWork W2015538044 @default.
- W3162187798 hasRelatedWork W2900794075 @default.
- W3162187798 hasRelatedWork W2961085424 @default.
- W3162187798 hasRelatedWork W3040041177 @default.
- W3162187798 hasRelatedWork W3183633970 @default.
- W3162187798 hasRelatedWork W3200266554 @default.
- W3162187798 hasRelatedWork W3208309985 @default.
- W3162187798 hasRelatedWork W4289653936 @default.
- W3162187798 hasRelatedWork W4306674287 @default.
- W3162187798 hasRelatedWork W2164844972 @default.
- W3162187798 isParatext "false" @default.
- W3162187798 isRetracted "false" @default.
- W3162187798 magId "3162187798" @default.
- W3162187798 workType "article" @default.