Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200234862> ?p ?o ?g. }
- W4200234862 endingPage "961" @default.
- W4200234862 startingPage "949" @default.
- W4200234862 abstract "Hashing is a practical approach for the approximate nearest neighbor search. Deep hashing methods, which train deep networks to generate compact and similarity-preserving binary codes for entities (e.g. images), have received lots of attention in the information retrieval community. A representative stream of deep hashing methods is triplet-based hashing that learns hashing models from triplets of data. The existing triplet-based hashing methods only consider triplets that are in the form of (q,q+,q-) , where q and q+ are in the same class and q and q- are in different classes. However, the number of possible triplets is approximately the cube of training examples, triplets used in the existing methods are only a small fraction of all possible triplets. This motivates us to develop a new triplet-based hashing method that adopts many more triplets in training phase. We propose Deep Listwise Triplet Hashing (DLTH) that introduces more triplets into batch-based training and a novel listwise triplet loss to capture the relative similarity in new triplets. This method has a pipeline of two steps. In Step 1, we propose a novel way to generate triplets from the soft class labels obtained by knowledge distillation module, where the triplets in the form of (q,q+,q-) are a subset of the newly obtained triplets. In Step 2, we develop a novel listwise triplet loss to train the hashing network, which seeks to capture the relative similarity between images in triplets according to soft labels. We conduct comprehensive image retrieval experiments on four benchmark datasets. The experimental results show that the proposed method has superior performances over state-of-the-art baselines." @default.
- W4200234862 created "2021-12-31" @default.
- W4200234862 creator A5004557206 @default.
- W4200234862 creator A5017205177 @default.
- W4200234862 creator A5025997006 @default.
- W4200234862 creator A5076868018 @default.
- W4200234862 creator A5087294951 @default.
- W4200234862 date "2022-01-01" @default.
- W4200234862 modified "2023-10-14" @default.
- W4200234862 title "Deep Listwise Triplet Hashing for Fine-Grained Image Retrieval" @default.
- W4200234862 cites W1939575207 @default.
- W4200234862 cites W1972702299 @default.
- W4200234862 cites W1974647172 @default.
- W4200234862 cites W1996936615 @default.
- W4200234862 cites W2017814585 @default.
- W4200234862 cites W2091158010 @default.
- W4200234862 cites W2108862644 @default.
- W4200234862 cites W2125398996 @default.
- W4200234862 cites W2138011018 @default.
- W4200234862 cites W2143331230 @default.
- W4200234862 cites W2151103935 @default.
- W4200234862 cites W2161969291 @default.
- W4200234862 cites W2171790913 @default.
- W4200234862 cites W2183341477 @default.
- W4200234862 cites W2194775991 @default.
- W4200234862 cites W2464915613 @default.
- W4200234862 cites W2471768434 @default.
- W4200234862 cites W2579318141 @default.
- W4200234862 cites W2737725206 @default.
- W4200234862 cites W2739879705 @default.
- W4200234862 cites W2741447225 @default.
- W4200234862 cites W2743289088 @default.
- W4200234862 cites W2773003563 @default.
- W4200234862 cites W2798834175 @default.
- W4200234862 cites W2895347732 @default.
- W4200234862 cites W2897656415 @default.
- W4200234862 cites W2940791172 @default.
- W4200234862 cites W2949710344 @default.
- W4200234862 cites W2959289524 @default.
- W4200234862 cites W2961018736 @default.
- W4200234862 cites W2963026686 @default.
- W4200234862 cites W2963154697 @default.
- W4200234862 cites W2963263909 @default.
- W4200234862 cites W2963448345 @default.
- W4200234862 cites W2964076257 @default.
- W4200234862 cites W2964181521 @default.
- W4200234862 cites W2964271799 @default.
- W4200234862 cites W2964280870 @default.
- W4200234862 cites W2965898445 @default.
- W4200234862 cites W2991691693 @default.
- W4200234862 cites W3011666149 @default.
- W4200234862 cites W3021521120 @default.
- W4200234862 cites W3035014997 @default.
- W4200234862 cites W3099206234 @default.
- W4200234862 cites W3108560336 @default.
- W4200234862 cites W3116704196 @default.
- W4200234862 cites W3125882365 @default.
- W4200234862 doi "https://doi.org/10.1109/tip.2021.3137653" @default.
- W4200234862 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34965208" @default.
- W4200234862 hasPublicationYear "2022" @default.
- W4200234862 type Work @default.
- W4200234862 citedByCount "6" @default.
- W4200234862 countsByYear W42002348622022 @default.
- W4200234862 countsByYear W42002348622023 @default.
- W4200234862 crossrefType "journal-article" @default.
- W4200234862 hasAuthorship W4200234862A5004557206 @default.
- W4200234862 hasAuthorship W4200234862A5017205177 @default.
- W4200234862 hasAuthorship W4200234862A5025997006 @default.
- W4200234862 hasAuthorship W4200234862A5076868018 @default.
- W4200234862 hasAuthorship W4200234862A5087294951 @default.
- W4200234862 hasConcept C103278499 @default.
- W4200234862 hasConcept C115961682 @default.
- W4200234862 hasConcept C153180895 @default.
- W4200234862 hasConcept C154945302 @default.
- W4200234862 hasConcept C1667742 @default.
- W4200234862 hasConcept C33923547 @default.
- W4200234862 hasConcept C38652104 @default.
- W4200234862 hasConcept C41008148 @default.
- W4200234862 hasConcept C48372109 @default.
- W4200234862 hasConcept C63435697 @default.
- W4200234862 hasConcept C67388219 @default.
- W4200234862 hasConcept C74270461 @default.
- W4200234862 hasConcept C94375191 @default.
- W4200234862 hasConcept C99138194 @default.
- W4200234862 hasConceptScore W4200234862C103278499 @default.
- W4200234862 hasConceptScore W4200234862C115961682 @default.
- W4200234862 hasConceptScore W4200234862C153180895 @default.
- W4200234862 hasConceptScore W4200234862C154945302 @default.
- W4200234862 hasConceptScore W4200234862C1667742 @default.
- W4200234862 hasConceptScore W4200234862C33923547 @default.
- W4200234862 hasConceptScore W4200234862C38652104 @default.
- W4200234862 hasConceptScore W4200234862C41008148 @default.
- W4200234862 hasConceptScore W4200234862C48372109 @default.
- W4200234862 hasConceptScore W4200234862C63435697 @default.
- W4200234862 hasConceptScore W4200234862C67388219 @default.
- W4200234862 hasConceptScore W4200234862C74270461 @default.
- W4200234862 hasConceptScore W4200234862C94375191 @default.
- W4200234862 hasConceptScore W4200234862C99138194 @default.