Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285606983> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4285606983 abstract "In this paper, we study deep unsupervised hashing, a critical problem for approximate nearest neighbor research. Most recent methods solve this problem by semantic similarity reconstruction for guiding hashing network learning or contrastive learning of hash codes. However, in multi-label scenarios, these methods usually either generate an inaccurate similarity matrix without reflection of similarity ranking or suffer from the violation of the underlying assumption in contrastive learning, resulting in limited retrieval performance. To tackle this issue, we propose a novel method termed HAMAN, which explores semantics from a fine-grained view to enhance the ability of multi-label image retrieval. In particular, we reconstruct the pairwise similarity structure by matching fine-grained patch features generated by the pre-trained neural network, serving as reliable guidance for similarity preserving of hash codes. Moreover, a novel conditional contrastive learning on hash codes is proposed to adopt self-supervised learning in multi-label scenarios. According to extensive experiments on three multi-label datasets, the proposed method outperforms a broad range of state-of-the-art methods." @default.
- W4285606983 created "2022-07-16" @default.
- W4285606983 creator A5015911476 @default.
- W4285606983 creator A5030001981 @default.
- W4285606983 creator A5030843117 @default.
- W4285606983 creator A5056726197 @default.
- W4285606983 creator A5067265615 @default.
- W4285606983 creator A5075496043 @default.
- W4285606983 creator A5082040765 @default.
- W4285606983 date "2022-07-01" @default.
- W4285606983 modified "2023-09-27" @default.
- W4285606983 title "Improved Deep Unsupervised Hashing with Fine-grained Semantic Similarity Mining for Multi-Label Image Retrieval" @default.
- W4285606983 doi "https://doi.org/10.24963/ijcai.2022/172" @default.
- W4285606983 hasPublicationYear "2022" @default.
- W4285606983 type Work @default.
- W4285606983 citedByCount "0" @default.
- W4285606983 crossrefType "proceedings-article" @default.
- W4285606983 hasAuthorship W4285606983A5015911476 @default.
- W4285606983 hasAuthorship W4285606983A5030001981 @default.
- W4285606983 hasAuthorship W4285606983A5030843117 @default.
- W4285606983 hasAuthorship W4285606983A5056726197 @default.
- W4285606983 hasAuthorship W4285606983A5067265615 @default.
- W4285606983 hasAuthorship W4285606983A5075496043 @default.
- W4285606983 hasAuthorship W4285606983A5082040765 @default.
- W4285606983 hasBestOaLocation W42856069831 @default.
- W4285606983 hasConcept C103278499 @default.
- W4285606983 hasConcept C108583219 @default.
- W4285606983 hasConcept C115961682 @default.
- W4285606983 hasConcept C116738811 @default.
- W4285606983 hasConcept C119857082 @default.
- W4285606983 hasConcept C130318100 @default.
- W4285606983 hasConcept C153180895 @default.
- W4285606983 hasConcept C154945302 @default.
- W4285606983 hasConcept C1667742 @default.
- W4285606983 hasConcept C184898388 @default.
- W4285606983 hasConcept C38652104 @default.
- W4285606983 hasConcept C41008148 @default.
- W4285606983 hasConcept C67388219 @default.
- W4285606983 hasConcept C74270461 @default.
- W4285606983 hasConcept C99138194 @default.
- W4285606983 hasConceptScore W4285606983C103278499 @default.
- W4285606983 hasConceptScore W4285606983C108583219 @default.
- W4285606983 hasConceptScore W4285606983C115961682 @default.
- W4285606983 hasConceptScore W4285606983C116738811 @default.
- W4285606983 hasConceptScore W4285606983C119857082 @default.
- W4285606983 hasConceptScore W4285606983C130318100 @default.
- W4285606983 hasConceptScore W4285606983C153180895 @default.
- W4285606983 hasConceptScore W4285606983C154945302 @default.
- W4285606983 hasConceptScore W4285606983C1667742 @default.
- W4285606983 hasConceptScore W4285606983C184898388 @default.
- W4285606983 hasConceptScore W4285606983C38652104 @default.
- W4285606983 hasConceptScore W4285606983C41008148 @default.
- W4285606983 hasConceptScore W4285606983C67388219 @default.
- W4285606983 hasConceptScore W4285606983C74270461 @default.
- W4285606983 hasConceptScore W4285606983C99138194 @default.
- W4285606983 hasLocation W42856069831 @default.
- W4285606983 hasOpenAccess W4285606983 @default.
- W4285606983 hasPrimaryLocation W42856069831 @default.
- W4285606983 hasRelatedWork W2121881251 @default.
- W4285606983 hasRelatedWork W2162881463 @default.
- W4285606983 hasRelatedWork W2768428796 @default.
- W4285606983 hasRelatedWork W2791305510 @default.
- W4285606983 hasRelatedWork W2963396503 @default.
- W4285606983 hasRelatedWork W2966218308 @default.
- W4285606983 hasRelatedWork W2980670924 @default.
- W4285606983 hasRelatedWork W3021521120 @default.
- W4285606983 hasRelatedWork W3094734909 @default.
- W4285606983 hasRelatedWork W3085483185 @default.
- W4285606983 isParatext "false" @default.
- W4285606983 isRetracted "false" @default.
- W4285606983 workType "article" @default.