Matches in SemOpenAlex for { <https://semopenalex.org/work/W2185348574> ?p ?o ?g. }
- W2185348574 abstract "We study the problem of multi-class image classification with large number of classes, of which the one-vs-all based approach is prohibitive in practical applications. Recent state-of-the-art approaches rely on label tree to reduce classification complexity. However, building optimal tree structures and learning precise classifiers to optimize tree loss is challenging. In this paper, we introduce a novel approach using latent classifiers that can achieve comparable speed but better performance. The key idea is that instead of using C one-vs-all classifiers (C is the number of classes) to generate the score matrix for label prediction, a much smaller number of classifiers are used. These classifiers, called latent classifiers, are generated by analyzing the correlation among classes and removing redundancy. Experiments on several large datasets including ImageNet-1K, SUN-397, and Caltech-256 show the efficiency of our approach." @default.
- W2185348574 created "2016-06-24" @default.
- W2185348574 creator A5006166354 @default.
- W2185348574 creator A5043063578 @default.
- W2185348574 creator A5053580743 @default.
- W2185348574 creator A5058707590 @default.
- W2185348574 creator A5078878666 @default.
- W2185348574 creator A5081841048 @default.
- W2185348574 date "2015-10-01" @default.
- W2185348574 modified "2023-10-07" @default.
- W2185348574 title "Large scale multi-class classification using latent classifiers" @default.
- W2185348574 cites W1576445103 @default.
- W2185348574 cites W1676820704 @default.
- W2185348574 cites W1967732418 @default.
- W2185348574 cites W1978962787 @default.
- W2185348574 cites W2017814585 @default.
- W2185348574 cites W2027922120 @default.
- W2185348574 cites W2053229256 @default.
- W2185348574 cites W2066941820 @default.
- W2185348574 cites W2095181741 @default.
- W2185348574 cites W2101276256 @default.
- W2185348574 cites W2106624428 @default.
- W2185348574 cites W2111993661 @default.
- W2185348574 cites W2117539524 @default.
- W2185348574 cites W2118585731 @default.
- W2185348574 cites W2120725344 @default.
- W2185348574 cites W2133864802 @default.
- W2185348574 cites W2155144632 @default.
- W2185348574 cites W2157065343 @default.
- W2185348574 cites W2162915993 @default.
- W2185348574 cites W2542395431 @default.
- W2185348574 doi "https://doi.org/10.1109/mmsp.2015.7340800" @default.
- W2185348574 hasPublicationYear "2015" @default.
- W2185348574 type Work @default.
- W2185348574 sameAs 2185348574 @default.
- W2185348574 citedByCount "0" @default.
- W2185348574 crossrefType "proceedings-article" @default.
- W2185348574 hasAuthorship W2185348574A5006166354 @default.
- W2185348574 hasAuthorship W2185348574A5043063578 @default.
- W2185348574 hasAuthorship W2185348574A5053580743 @default.
- W2185348574 hasAuthorship W2185348574A5058707590 @default.
- W2185348574 hasAuthorship W2185348574A5078878666 @default.
- W2185348574 hasAuthorship W2185348574A5081841048 @default.
- W2185348574 hasConcept C106135958 @default.
- W2185348574 hasConcept C111919701 @default.
- W2185348574 hasConcept C113174947 @default.
- W2185348574 hasConcept C115961682 @default.
- W2185348574 hasConcept C119857082 @default.
- W2185348574 hasConcept C12267149 @default.
- W2185348574 hasConcept C124101348 @default.
- W2185348574 hasConcept C134306372 @default.
- W2185348574 hasConcept C152124472 @default.
- W2185348574 hasConcept C153180895 @default.
- W2185348574 hasConcept C154945302 @default.
- W2185348574 hasConcept C2777212361 @default.
- W2185348574 hasConcept C33923547 @default.
- W2185348574 hasConcept C41008148 @default.
- W2185348574 hasConcept C75294576 @default.
- W2185348574 hasConcept C84525736 @default.
- W2185348574 hasConceptScore W2185348574C106135958 @default.
- W2185348574 hasConceptScore W2185348574C111919701 @default.
- W2185348574 hasConceptScore W2185348574C113174947 @default.
- W2185348574 hasConceptScore W2185348574C115961682 @default.
- W2185348574 hasConceptScore W2185348574C119857082 @default.
- W2185348574 hasConceptScore W2185348574C12267149 @default.
- W2185348574 hasConceptScore W2185348574C124101348 @default.
- W2185348574 hasConceptScore W2185348574C134306372 @default.
- W2185348574 hasConceptScore W2185348574C152124472 @default.
- W2185348574 hasConceptScore W2185348574C153180895 @default.
- W2185348574 hasConceptScore W2185348574C154945302 @default.
- W2185348574 hasConceptScore W2185348574C2777212361 @default.
- W2185348574 hasConceptScore W2185348574C33923547 @default.
- W2185348574 hasConceptScore W2185348574C41008148 @default.
- W2185348574 hasConceptScore W2185348574C75294576 @default.
- W2185348574 hasConceptScore W2185348574C84525736 @default.
- W2185348574 hasLocation W21853485741 @default.
- W2185348574 hasOpenAccess W2185348574 @default.
- W2185348574 hasPrimaryLocation W21853485741 @default.
- W2185348574 hasRelatedWork W118170734 @default.
- W2185348574 hasRelatedWork W2013477326 @default.
- W2185348574 hasRelatedWork W2132573811 @default.
- W2185348574 hasRelatedWork W2165848327 @default.
- W2185348574 hasRelatedWork W2188767201 @default.
- W2185348574 hasRelatedWork W2209908269 @default.
- W2185348574 hasRelatedWork W2293042980 @default.
- W2185348574 hasRelatedWork W2807776403 @default.
- W2185348574 hasRelatedWork W2890622213 @default.
- W2185348574 hasRelatedWork W2922886970 @default.
- W2185348574 hasRelatedWork W2986554109 @default.
- W2185348574 hasRelatedWork W2988012434 @default.
- W2185348574 hasRelatedWork W2996611057 @default.
- W2185348574 hasRelatedWork W3014040748 @default.
- W2185348574 hasRelatedWork W3017564402 @default.
- W2185348574 hasRelatedWork W3108150634 @default.
- W2185348574 hasRelatedWork W3118534112 @default.
- W2185348574 hasRelatedWork W3202048315 @default.
- W2185348574 hasRelatedWork W2189351672 @default.
- W2185348574 hasRelatedWork W2868566551 @default.
- W2185348574 isParatext "false" @default.
- W2185348574 isRetracted "false" @default.