Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367047204> ?p ?o ?g. }
- W4367047204 abstract "This paper studies unsupervised domain adaptive hashing, which aims to transfer a hashing model from a label-rich source domain to a label-scarce target domain. Current state-of-the-art approaches generally resolve the problem by integrating pseudo-labeling and domain adaptation techniques into deep hashing paradigms. Nevertheless, they usually suffer from serious class imbalance in pseudo-labels and suboptimal domain alignment caused by the neglection of the intrinsic structures of two domains. To address this issue, we propose a novel method named unbiaseD duAl hashiNg Contrastive lEarning (DANCE) for domain adaptive image retrieval. The core of our DANCE is to perform contrastive learning on hash codes from both instance level and prototype level. To begin, DANCE utilizes label information to guide instance-level hashing contrastive learning in the source domain. To generate unbiased and reliable pseudo-labels for semantic learning in the target domain, we uniformly select samples around each label embedding in the Hamming space. A momentum-update scheme is also utilized to smooth the optimization process. Additionally, we measure the semantic prototype representations in both source and target domains and incorporate them into a domain-aware prototype-level contrastive learning paradigm, which enhances domain alignment in the Hamming space while maximizing the model capacity. Experimental results on a number of well-known domain adaptive retrieval benchmarks validate the effectiveness of our proposed DANCE compared to a variety of competing baselines in different settings." @default.
- W4367047204 created "2023-04-27" @default.
- W4367047204 creator A5001181973 @default.
- W4367047204 creator A5001452098 @default.
- W4367047204 creator A5003334435 @default.
- W4367047204 creator A5014265339 @default.
- W4367047204 creator A5024965898 @default.
- W4367047204 creator A5072710764 @default.
- W4367047204 creator A5073859117 @default.
- W4367047204 date "2023-04-30" @default.
- W4367047204 modified "2023-10-17" @default.
- W4367047204 title "DANCE: Learning A Domain Adaptive Framework for Deep Hashing" @default.
- W4367047204 cites W1722318740 @default.
- W4367047204 cites W1974647172 @default.
- W4367047204 cites W2040918046 @default.
- W4367047204 cites W2057266281 @default.
- W4367047204 cites W2100659887 @default.
- W4367047204 cites W2112796928 @default.
- W4367047204 cites W2411707397 @default.
- W4367047204 cites W2627183927 @default.
- W4367047204 cites W2749777401 @default.
- W4367047204 cites W2765440071 @default.
- W4367047204 cites W2766724094 @default.
- W4367047204 cites W2795832645 @default.
- W4367047204 cites W2798702669 @default.
- W4367047204 cites W2799787995 @default.
- W4367047204 cites W2890032859 @default.
- W4367047204 cites W2922521335 @default.
- W4367047204 cites W2945806531 @default.
- W4367047204 cites W2962687275 @default.
- W4367047204 cites W2964158883 @default.
- W4367047204 cites W2966088020 @default.
- W4367047204 cites W2967957126 @default.
- W4367047204 cites W2975761438 @default.
- W4367047204 cites W2978274700 @default.
- W4367047204 cites W2980096013 @default.
- W4367047204 cites W2981496068 @default.
- W4367047204 cites W3012642003 @default.
- W4367047204 cites W3012833893 @default.
- W4367047204 cites W3034239448 @default.
- W4367047204 cites W3034315422 @default.
- W4367047204 cites W3034971598 @default.
- W4367047204 cites W3035524453 @default.
- W4367047204 cites W3035732386 @default.
- W4367047204 cites W3087124270 @default.
- W4367047204 cites W3093265782 @default.
- W4367047204 cites W3114063012 @default.
- W4367047204 cites W3153783849 @default.
- W4367047204 cites W3154134332 @default.
- W4367047204 cites W3155638432 @default.
- W4367047204 cites W3155787390 @default.
- W4367047204 cites W3187985423 @default.
- W4367047204 cites W3188087362 @default.
- W4367047204 cites W3207182362 @default.
- W4367047204 cites W4214697508 @default.
- W4367047204 cites W4224241592 @default.
- W4367047204 cites W4224324956 @default.
- W4367047204 cites W4225580830 @default.
- W4367047204 cites W4226333663 @default.
- W4367047204 cites W4285604435 @default.
- W4367047204 cites W4304092162 @default.
- W4367047204 cites W4312416205 @default.
- W4367047204 cites W4312496732 @default.
- W4367047204 cites W4312601326 @default.
- W4367047204 cites W4319878852 @default.
- W4367047204 cites W74601114 @default.
- W4367047204 doi "https://doi.org/10.1145/3543507.3583445" @default.
- W4367047204 hasPublicationYear "2023" @default.
- W4367047204 type Work @default.
- W4367047204 citedByCount "0" @default.
- W4367047204 crossrefType "proceedings-article" @default.
- W4367047204 hasAuthorship W4367047204A5001181973 @default.
- W4367047204 hasAuthorship W4367047204A5001452098 @default.
- W4367047204 hasAuthorship W4367047204A5003334435 @default.
- W4367047204 hasAuthorship W4367047204A5014265339 @default.
- W4367047204 hasAuthorship W4367047204A5024965898 @default.
- W4367047204 hasAuthorship W4367047204A5072710764 @default.
- W4367047204 hasAuthorship W4367047204A5073859117 @default.
- W4367047204 hasBestOaLocation W43670472041 @default.
- W4367047204 hasConcept C116058348 @default.
- W4367047204 hasConcept C119857082 @default.
- W4367047204 hasConcept C133667856 @default.
- W4367047204 hasConcept C134306372 @default.
- W4367047204 hasConcept C138111711 @default.
- W4367047204 hasConcept C153180895 @default.
- W4367047204 hasConcept C154945302 @default.
- W4367047204 hasConcept C33923547 @default.
- W4367047204 hasConcept C36503486 @default.
- W4367047204 hasConcept C38652104 @default.
- W4367047204 hasConcept C41008148 @default.
- W4367047204 hasConcept C67388219 @default.
- W4367047204 hasConcept C74270461 @default.
- W4367047204 hasConcept C80444323 @default.
- W4367047204 hasConcept C99138194 @default.
- W4367047204 hasConceptScore W4367047204C116058348 @default.
- W4367047204 hasConceptScore W4367047204C119857082 @default.
- W4367047204 hasConceptScore W4367047204C133667856 @default.
- W4367047204 hasConceptScore W4367047204C134306372 @default.
- W4367047204 hasConceptScore W4367047204C138111711 @default.
- W4367047204 hasConceptScore W4367047204C153180895 @default.