Matches in SemOpenAlex for { <https://semopenalex.org/work/W3164058237> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W3164058237 abstract "Person re-identification (re-ID) aims to establish identity correspondence across different cameras. State-of-the-art re-ID approaches are mainly clustering-based Unsupervised Domain Adaptation (UDA) methods, which attempt to transfer the model trained on the source domain to target domain, by alternatively generating pseudo labels by clustering target-domain instances and training the network with generated pseudo labels to perform feature learning. However, these approaches suffer from the problem of inevitable label noise caused by the clustering procedure that dramatically impact the model training and feature learning of the target domain. To address this issue, we propose an unsupervised Hierarchical Clustering via Mutual Learning (HCML) framework, which can jointly optimize the dual training network and the clustering procedure to learn more discriminative features from the target domain. Specifically, the proposed HCML framework can effectively update the hard pseudo labels generated by clustering process and soft pseudo label generated by the training network both in on-line manner. We jointly adopt the repelled loss, triplet loss, soft identity loss and soft triplet loss to optimize the model. The experimental results on Market-to-Duke, Duke-to-Market, Market-to-MSMT and Duke-to-MSMT unsupervised domain adaptation tasks have demonstrated the superiority of our proposed HCML framework compared with other state-of-the-art methods." @default.
- W3164058237 created "2021-06-07" @default.
- W3164058237 creator A5009173399 @default.
- W3164058237 creator A5014888334 @default.
- W3164058237 creator A5062752598 @default.
- W3164058237 creator A5086751993 @default.
- W3164058237 date "2020-01-01" @default.
- W3164058237 modified "2023-09-23" @default.
- W3164058237 title "Hierarchical clustering via mutual learning for unsupervised person re-identification." @default.
- W3164058237 hasPublicationYear "2020" @default.
- W3164058237 type Work @default.
- W3164058237 sameAs 3164058237 @default.
- W3164058237 citedByCount "0" @default.
- W3164058237 crossrefType "journal-article" @default.
- W3164058237 hasAuthorship W3164058237A5009173399 @default.
- W3164058237 hasAuthorship W3164058237A5014888334 @default.
- W3164058237 hasAuthorship W3164058237A5062752598 @default.
- W3164058237 hasAuthorship W3164058237A5086751993 @default.
- W3164058237 hasConcept C116834253 @default.
- W3164058237 hasConcept C119857082 @default.
- W3164058237 hasConcept C134306372 @default.
- W3164058237 hasConcept C138885662 @default.
- W3164058237 hasConcept C153180895 @default.
- W3164058237 hasConcept C154945302 @default.
- W3164058237 hasConcept C2776401178 @default.
- W3164058237 hasConcept C33923547 @default.
- W3164058237 hasConcept C36503486 @default.
- W3164058237 hasConcept C41008148 @default.
- W3164058237 hasConcept C41895202 @default.
- W3164058237 hasConcept C59822182 @default.
- W3164058237 hasConcept C73555534 @default.
- W3164058237 hasConcept C8038995 @default.
- W3164058237 hasConcept C86803240 @default.
- W3164058237 hasConcept C97931131 @default.
- W3164058237 hasConceptScore W3164058237C116834253 @default.
- W3164058237 hasConceptScore W3164058237C119857082 @default.
- W3164058237 hasConceptScore W3164058237C134306372 @default.
- W3164058237 hasConceptScore W3164058237C138885662 @default.
- W3164058237 hasConceptScore W3164058237C153180895 @default.
- W3164058237 hasConceptScore W3164058237C154945302 @default.
- W3164058237 hasConceptScore W3164058237C2776401178 @default.
- W3164058237 hasConceptScore W3164058237C33923547 @default.
- W3164058237 hasConceptScore W3164058237C36503486 @default.
- W3164058237 hasConceptScore W3164058237C41008148 @default.
- W3164058237 hasConceptScore W3164058237C41895202 @default.
- W3164058237 hasConceptScore W3164058237C59822182 @default.
- W3164058237 hasConceptScore W3164058237C73555534 @default.
- W3164058237 hasConceptScore W3164058237C8038995 @default.
- W3164058237 hasConceptScore W3164058237C86803240 @default.
- W3164058237 hasConceptScore W3164058237C97931131 @default.
- W3164058237 hasLocation W31640582371 @default.
- W3164058237 hasOpenAccess W3164058237 @default.
- W3164058237 hasPrimaryLocation W31640582371 @default.
- W3164058237 hasRelatedWork W2895281799 @default.
- W3164058237 hasRelatedWork W2897536120 @default.
- W3164058237 hasRelatedWork W2929779797 @default.
- W3164058237 hasRelatedWork W2948462823 @default.
- W3164058237 hasRelatedWork W2990782765 @default.
- W3164058237 hasRelatedWork W2991420006 @default.
- W3164058237 hasRelatedWork W2995852213 @default.
- W3164058237 hasRelatedWork W2996946635 @default.
- W3164058237 hasRelatedWork W3022622233 @default.
- W3164058237 hasRelatedWork W3089771107 @default.
- W3164058237 hasRelatedWork W3108755323 @default.
- W3164058237 hasRelatedWork W3110703445 @default.
- W3164058237 hasRelatedWork W3137858533 @default.
- W3164058237 hasRelatedWork W3143162580 @default.
- W3164058237 hasRelatedWork W3158710282 @default.
- W3164058237 hasRelatedWork W3159381233 @default.
- W3164058237 hasRelatedWork W3184360601 @default.
- W3164058237 hasRelatedWork W3204665409 @default.
- W3164058237 hasRelatedWork W3208534251 @default.
- W3164058237 hasRelatedWork W3210967702 @default.
- W3164058237 isParatext "false" @default.
- W3164058237 isRetracted "false" @default.
- W3164058237 magId "3164058237" @default.
- W3164058237 workType "article" @default.