Matches in SemOpenAlex for { <https://semopenalex.org/work/W3003592305> ?p ?o ?g. }
- W3003592305 abstract "In this paper we propose an approach for learning low dimensional optimized feature space with minimum intra-class variance and maximum inter-class variance. We address the problem of high-dimensionality of feature vectors extracted from neural networks by taking care of the global statistics of feature space. Classical approach of Linear Discriminant Analysis (LDA) is generally used for generating an optimized low dimensional feature space for single-labeled images. Since, image retrieval involves both multi-labeled and single-labeled images, we utilize the equivalence between LDA and Canonical Correlation Analysis (CCA) to generate an optimized feature space for single-labeled images and use CCA to generate an optimized feature space for multi-labeled images. Our approach correlates the projections of feature vectors with label vectors in our CCA based network architecture. The neural network minimize a loss function which maximizes the correlation coefficients. We binarize our generated feature vectors with the popular Iterative Quantization (ITQ) approach and also propose an ensemble network to generate binary codes of desired bit length for image retrieval. Our measurement of mean average precision shows competitive results on other state-of-the-art single-labeled and multi-labeled image retrieval datasets." @default.
- W3003592305 created "2020-02-07" @default.
- W3003592305 creator A5018820700 @default.
- W3003592305 creator A5023199409 @default.
- W3003592305 creator A5045397738 @default.
- W3003592305 creator A5070898273 @default.
- W3003592305 date "2020-01-30" @default.
- W3003592305 modified "2023-09-27" @default.
- W3003592305 title "Optimized Feature Space Learning for Generating Efficient Binary Codes for Image Retrieval" @default.
- W3003592305 cites W1502916507 @default.
- W3003592305 cites W1523385540 @default.
- W3003592305 cites W1910300841 @default.
- W3003592305 cites W1939575207 @default.
- W3003592305 cites W1966385142 @default.
- W3003592305 cites W1972853352 @default.
- W3003592305 cites W1974647172 @default.
- W3003592305 cites W1992371516 @default.
- W3003592305 cites W1996936615 @default.
- W3003592305 cites W2001619934 @default.
- W3003592305 cites W2007972815 @default.
- W3003592305 cites W2012592962 @default.
- W3003592305 cites W2025341678 @default.
- W3003592305 cites W2036279918 @default.
- W3003592305 cites W204268067 @default.
- W3003592305 cites W2058307353 @default.
- W3003592305 cites W2100235303 @default.
- W3003592305 cites W2111993661 @default.
- W3003592305 cites W2113180829 @default.
- W3003592305 cites W2117228865 @default.
- W3003592305 cites W2130660124 @default.
- W3003592305 cites W2136414491 @default.
- W3003592305 cites W2163605009 @default.
- W3003592305 cites W2164338181 @default.
- W3003592305 cites W2166658544 @default.
- W3003592305 cites W2187089797 @default.
- W3003592305 cites W2207125444 @default.
- W3003592305 cites W2261252251 @default.
- W3003592305 cites W2293597654 @default.
- W3003592305 cites W2293824885 @default.
- W3003592305 cites W2411707397 @default.
- W3003592305 cites W2461086877 @default.
- W3003592305 cites W2464915613 @default.
- W3003592305 cites W2499468060 @default.
- W3003592305 cites W2508837377 @default.
- W3003592305 cites W2510911086 @default.
- W3003592305 cites W2562137921 @default.
- W3003592305 cites W2562322388 @default.
- W3003592305 cites W2565993688 @default.
- W3003592305 cites W2566357401 @default.
- W3003592305 cites W2612930127 @default.
- W3003592305 cites W2781821509 @default.
- W3003592305 cites W2963173190 @default.
- W3003592305 cites W2963276379 @default.
- W3003592305 cites W2963540428 @default.
- W3003592305 cites W2964280870 @default.
- W3003592305 cites W3118608800 @default.
- W3003592305 cites W840129875 @default.
- W3003592305 hasPublicationYear "2020" @default.
- W3003592305 type Work @default.
- W3003592305 sameAs 3003592305 @default.
- W3003592305 citedByCount "0" @default.
- W3003592305 crossrefType "posted-content" @default.
- W3003592305 hasAuthorship W3003592305A5018820700 @default.
- W3003592305 hasAuthorship W3003592305A5023199409 @default.
- W3003592305 hasAuthorship W3003592305A5045397738 @default.
- W3003592305 hasAuthorship W3003592305A5070898273 @default.
- W3003592305 hasConcept C111030470 @default.
- W3003592305 hasConcept C115961682 @default.
- W3003592305 hasConcept C138885662 @default.
- W3003592305 hasConcept C153180895 @default.
- W3003592305 hasConcept C154945302 @default.
- W3003592305 hasConcept C1667742 @default.
- W3003592305 hasConcept C2776401178 @default.
- W3003592305 hasConcept C33923547 @default.
- W3003592305 hasConcept C41008148 @default.
- W3003592305 hasConcept C41895202 @default.
- W3003592305 hasConcept C69738355 @default.
- W3003592305 hasConcept C70518039 @default.
- W3003592305 hasConcept C83665646 @default.
- W3003592305 hasConceptScore W3003592305C111030470 @default.
- W3003592305 hasConceptScore W3003592305C115961682 @default.
- W3003592305 hasConceptScore W3003592305C138885662 @default.
- W3003592305 hasConceptScore W3003592305C153180895 @default.
- W3003592305 hasConceptScore W3003592305C154945302 @default.
- W3003592305 hasConceptScore W3003592305C1667742 @default.
- W3003592305 hasConceptScore W3003592305C2776401178 @default.
- W3003592305 hasConceptScore W3003592305C33923547 @default.
- W3003592305 hasConceptScore W3003592305C41008148 @default.
- W3003592305 hasConceptScore W3003592305C41895202 @default.
- W3003592305 hasConceptScore W3003592305C69738355 @default.
- W3003592305 hasConceptScore W3003592305C70518039 @default.
- W3003592305 hasConceptScore W3003592305C83665646 @default.
- W3003592305 hasLocation W30035923051 @default.
- W3003592305 hasOpenAccess W3003592305 @default.
- W3003592305 hasPrimaryLocation W30035923051 @default.
- W3003592305 hasRelatedWork W1511300029 @default.
- W3003592305 hasRelatedWork W2063064098 @default.
- W3003592305 hasRelatedWork W2065675582 @default.
- W3003592305 hasRelatedWork W2359360576 @default.
- W3003592305 hasRelatedWork W2391670136 @default.