Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312492074> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4312492074 abstract "Semantic hashing is a crucial component of content based search and retrieval systems. To achieve an effective semantic hashing for images, it is essential to map them to hash space in a way that preserves the semantic information. Most state-of-the-art deep semantic hashing approaches do not fully take into account the structural information and the inherent hierarchy in the dataset. Also, the distribution of hash codes is primarily driven by semantic information that comes from the supervision labels. We propose a semantic hashing framework which utilizes the hyperbolic metric learning to learn the structural and hierarchical information. This information is leveraged in the form of proxy labels for training the hashing network with the proposed novel Structure-Semantic Disagreement (SSD) loss. SSD enforces the model to learn to hash with semantic as well as structural information, leading to more robust and uniformly distributed hash codes. Tests on multiple public domain datasets establish the effectiveness of the proposed approach. Moreover, the developed SSD loss can also be applied to other classification models to improve the representation by enforcing the model to use the structure information more effectively." @default.
- W4312492074 created "2023-01-05" @default.
- W4312492074 creator A5029164573 @default.
- W4312492074 creator A5038006529 @default.
- W4312492074 creator A5081683515 @default.
- W4312492074 date "2022-09-26" @default.
- W4312492074 modified "2023-10-16" @default.
- W4312492074 title "Deep Semantic Hashing with Structure-Semantic Disagreement Correction via Hyperbolic Metric Learning" @default.
- W4312492074 cites W1910300841 @default.
- W4312492074 cites W1939575207 @default.
- W4312492074 cites W1974647172 @default.
- W4312492074 cites W1996936615 @default.
- W4312492074 cites W2007972815 @default.
- W4312492074 cites W2019464758 @default.
- W4312492074 cites W2024922353 @default.
- W4312492074 cites W2153273131 @default.
- W4312492074 cites W2293824885 @default.
- W4312492074 cites W2464915613 @default.
- W4312492074 cites W2508837377 @default.
- W4312492074 cites W2530345236 @default.
- W4312492074 cites W2594105920 @default.
- W4312492074 cites W2740912563 @default.
- W4312492074 cites W2766724094 @default.
- W4312492074 cites W2962786441 @default.
- W4312492074 cites W2980275434 @default.
- W4312492074 cites W3021893287 @default.
- W4312492074 cites W3176793698 @default.
- W4312492074 doi "https://doi.org/10.1109/mmsp55362.2022.9948733" @default.
- W4312492074 hasPublicationYear "2022" @default.
- W4312492074 type Work @default.
- W4312492074 citedByCount "0" @default.
- W4312492074 crossrefType "proceedings-article" @default.
- W4312492074 hasAuthorship W4312492074A5029164573 @default.
- W4312492074 hasAuthorship W4312492074A5038006529 @default.
- W4312492074 hasAuthorship W4312492074A5081683515 @default.
- W4312492074 hasConcept C116058348 @default.
- W4312492074 hasConcept C130318100 @default.
- W4312492074 hasConcept C138111711 @default.
- W4312492074 hasConcept C154945302 @default.
- W4312492074 hasConcept C166423231 @default.
- W4312492074 hasConcept C2129575 @default.
- W4312492074 hasConcept C23123220 @default.
- W4312492074 hasConcept C38652104 @default.
- W4312492074 hasConcept C41008148 @default.
- W4312492074 hasConcept C67388219 @default.
- W4312492074 hasConcept C80444323 @default.
- W4312492074 hasConcept C99138194 @default.
- W4312492074 hasConceptScore W4312492074C116058348 @default.
- W4312492074 hasConceptScore W4312492074C130318100 @default.
- W4312492074 hasConceptScore W4312492074C138111711 @default.
- W4312492074 hasConceptScore W4312492074C154945302 @default.
- W4312492074 hasConceptScore W4312492074C166423231 @default.
- W4312492074 hasConceptScore W4312492074C2129575 @default.
- W4312492074 hasConceptScore W4312492074C23123220 @default.
- W4312492074 hasConceptScore W4312492074C38652104 @default.
- W4312492074 hasConceptScore W4312492074C41008148 @default.
- W4312492074 hasConceptScore W4312492074C67388219 @default.
- W4312492074 hasConceptScore W4312492074C80444323 @default.
- W4312492074 hasConceptScore W4312492074C99138194 @default.
- W4312492074 hasLocation W43124920741 @default.
- W4312492074 hasOpenAccess W4312492074 @default.
- W4312492074 hasPrimaryLocation W43124920741 @default.
- W4312492074 hasRelatedWork W1489218338 @default.
- W4312492074 hasRelatedWork W1870428314 @default.
- W4312492074 hasRelatedWork W2146184373 @default.
- W4312492074 hasRelatedWork W2146912220 @default.
- W4312492074 hasRelatedWork W2159176173 @default.
- W4312492074 hasRelatedWork W2380556669 @default.
- W4312492074 hasRelatedWork W2533956867 @default.
- W4312492074 hasRelatedWork W2966317124 @default.
- W4312492074 hasRelatedWork W4206377746 @default.
- W4312492074 hasRelatedWork W4312492074 @default.
- W4312492074 isParatext "false" @default.
- W4312492074 isRetracted "false" @default.
- W4312492074 workType "article" @default.