Matches in SemOpenAlex for { <https://semopenalex.org/work/W2894793212> ?p ?o ?g. }
- W2894793212 abstract "The conventional supervised hashing methods based on classification do not entirely meet the requirements of hashing technique, but Linear Discriminant Analysis (LDA) does. In this paper, we propose to perform a revised LDA objective over deep networks to learn efficient hashing codes in a truly end-to-end fashion. However, the complicated eigenvalue decomposition within each mini-batch in every epoch has to be faced with when simply optimizing the deep network w.r.t. the LDA objective. In this work, the revised LDA objective is transformed into a simple least square problem, which naturally overcomes the intractable problems and can be easily solved by the off-the-shelf optimizer. Such deep extension can also overcome the weakness of LDA Hashing in the limited linear projection and feature learning. Amounts of experiments are conducted on three benchmark datasets. The proposed Deep LDA Hashing shows nearly 70 points improvement over the conventional one on the CIFAR-10 dataset. It also beats several state-of-the-art methods on various metrics." @default.
- W2894793212 created "2018-10-12" @default.
- W2894793212 creator A5003222421 @default.
- W2894793212 creator A5034766866 @default.
- W2894793212 creator A5068918243 @default.
- W2894793212 date "2018-10-08" @default.
- W2894793212 modified "2023-09-26" @default.
- W2894793212 title "Deep LDA Hashing" @default.
- W2894793212 cites W1974647172 @default.
- W2894793212 cites W1990537115 @default.
- W2894793212 cites W2014596061 @default.
- W2894793212 cites W2020111956 @default.
- W2894793212 cites W2046649434 @default.
- W2894793212 cites W2050025922 @default.
- W2894793212 cites W2098089028 @default.
- W2894793212 cites W2108598243 @default.
- W2894793212 cites W2112796928 @default.
- W2894793212 cites W2142881874 @default.
- W2894793212 cites W2143340430 @default.
- W2894793212 cites W2145065594 @default.
- W2894793212 cites W2152939563 @default.
- W2894793212 cites W2162006472 @default.
- W2894793212 cites W2164338181 @default.
- W2894793212 cites W2187089797 @default.
- W2894793212 cites W2207125444 @default.
- W2894793212 cites W2293597654 @default.
- W2894793212 cites W2294155285 @default.
- W2894793212 cites W2531549126 @default.
- W2894793212 cites W2557794022 @default.
- W2894793212 cites W2565993688 @default.
- W2894793212 cites W2586811659 @default.
- W2894793212 cites W2586937979 @default.
- W2894793212 cites W2604298190 @default.
- W2894793212 cites W2621176975 @default.
- W2894793212 cites W2913932916 @default.
- W2894793212 cites W2919115771 @default.
- W2894793212 cites W2951581059 @default.
- W2894793212 cites W2951692027 @default.
- W2894793212 cites W3118608800 @default.
- W2894793212 cites W862919699 @default.
- W2894793212 hasPublicationYear "2018" @default.
- W2894793212 type Work @default.
- W2894793212 sameAs 2894793212 @default.
- W2894793212 citedByCount "0" @default.
- W2894793212 crossrefType "posted-content" @default.
- W2894793212 hasAuthorship W2894793212A5003222421 @default.
- W2894793212 hasAuthorship W2894793212A5034766866 @default.
- W2894793212 hasAuthorship W2894793212A5068918243 @default.
- W2894793212 hasConcept C108583219 @default.
- W2894793212 hasConcept C11413529 @default.
- W2894793212 hasConcept C119857082 @default.
- W2894793212 hasConcept C13280743 @default.
- W2894793212 hasConcept C133667856 @default.
- W2894793212 hasConcept C138111711 @default.
- W2894793212 hasConcept C138885662 @default.
- W2894793212 hasConcept C153180895 @default.
- W2894793212 hasConcept C154945302 @default.
- W2894793212 hasConcept C185798385 @default.
- W2894793212 hasConcept C205649164 @default.
- W2894793212 hasConcept C2776401178 @default.
- W2894793212 hasConcept C38652104 @default.
- W2894793212 hasConcept C41008148 @default.
- W2894793212 hasConcept C41895202 @default.
- W2894793212 hasConcept C57493831 @default.
- W2894793212 hasConcept C67388219 @default.
- W2894793212 hasConcept C69738355 @default.
- W2894793212 hasConcept C99138194 @default.
- W2894793212 hasConceptScore W2894793212C108583219 @default.
- W2894793212 hasConceptScore W2894793212C11413529 @default.
- W2894793212 hasConceptScore W2894793212C119857082 @default.
- W2894793212 hasConceptScore W2894793212C13280743 @default.
- W2894793212 hasConceptScore W2894793212C133667856 @default.
- W2894793212 hasConceptScore W2894793212C138111711 @default.
- W2894793212 hasConceptScore W2894793212C138885662 @default.
- W2894793212 hasConceptScore W2894793212C153180895 @default.
- W2894793212 hasConceptScore W2894793212C154945302 @default.
- W2894793212 hasConceptScore W2894793212C185798385 @default.
- W2894793212 hasConceptScore W2894793212C205649164 @default.
- W2894793212 hasConceptScore W2894793212C2776401178 @default.
- W2894793212 hasConceptScore W2894793212C38652104 @default.
- W2894793212 hasConceptScore W2894793212C41008148 @default.
- W2894793212 hasConceptScore W2894793212C41895202 @default.
- W2894793212 hasConceptScore W2894793212C57493831 @default.
- W2894793212 hasConceptScore W2894793212C67388219 @default.
- W2894793212 hasConceptScore W2894793212C69738355 @default.
- W2894793212 hasConceptScore W2894793212C99138194 @default.
- W2894793212 hasLocation W28947932121 @default.
- W2894793212 hasOpenAccess W2894793212 @default.
- W2894793212 hasPrimaryLocation W28947932121 @default.
- W2894793212 hasRelatedWork W1910334602 @default.
- W2894793212 hasRelatedWork W2142881874 @default.
- W2894793212 hasRelatedWork W2405734658 @default.
- W2894793212 hasRelatedWork W2510312297 @default.
- W2894793212 hasRelatedWork W2519631826 @default.
- W2894793212 hasRelatedWork W2535084897 @default.
- W2894793212 hasRelatedWork W2535352129 @default.
- W2894793212 hasRelatedWork W2565993688 @default.
- W2894793212 hasRelatedWork W2592971341 @default.
- W2894793212 hasRelatedWork W2594800845 @default.
- W2894793212 hasRelatedWork W2741824037 @default.