Matches in SemOpenAlex for { <https://semopenalex.org/work/W2798956329> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2798956329 abstract "Deep learning to hash improves image retrieval performance by end-to-end representation learning and hash coding from training data with pairwise similarity information. Subject to the scarcity of similarity information that is often expensive to collect for many application domains, existing deep learning to hash methods may overfit the training data and result in substantial loss of retrieval quality. This paper presents HashGAN, a novel architecture for deep learning to hash, which learns compact binary hash codes from both real images and diverse images synthesized by generative models. The main idea is to augment the training data with nearly real images synthesized from a new Pair Conditional Wasserstein GAN (PC-WGAN) conditioned on the pairwise similarity information. Extensive experiments demonstrate that HashGAN can generate high-quality binary hash codes and yield state-of-the-art image retrieval performance on three benchmarks, NUS-WIDE, CIFAR-10, and MS-COCO." @default.
- W2798956329 created "2018-05-07" @default.
- W2798956329 creator A5000839872 @default.
- W2798956329 creator A5019241553 @default.
- W2798956329 creator A5028650738 @default.
- W2798956329 creator A5034579434 @default.
- W2798956329 date "2018-06-01" @default.
- W2798956329 modified "2023-09-25" @default.
- W2798956329 title "HashGAN: Deep Learning to Hash with Pair Conditional Wasserstein GAN" @default.
- W2798956329 cites W1910300841 @default.
- W2798956329 cites W1939575207 @default.
- W2798956329 cites W1956333070 @default.
- W2798956329 cites W1996936615 @default.
- W2798956329 cites W2007972815 @default.
- W2798956329 cites W2074668987 @default.
- W2798956329 cites W2084363474 @default.
- W2798956329 cites W2124509324 @default.
- W2798956329 cites W2147069236 @default.
- W2798956329 cites W2194775991 @default.
- W2798956329 cites W2388114291 @default.
- W2798956329 cites W2411707397 @default.
- W2798956329 cites W2464915613 @default.
- W2798956329 cites W2473499128 @default.
- W2798956329 cites W2733548594 @default.
- W2798956329 cites W2738649458 @default.
- W2798956329 cites W2964280870 @default.
- W2798956329 doi "https://doi.org/10.1109/cvpr.2018.00140" @default.
- W2798956329 hasPublicationYear "2018" @default.
- W2798956329 type Work @default.
- W2798956329 sameAs 2798956329 @default.
- W2798956329 citedByCount "92" @default.
- W2798956329 countsByYear W27989563292018 @default.
- W2798956329 countsByYear W27989563292019 @default.
- W2798956329 countsByYear W27989563292020 @default.
- W2798956329 countsByYear W27989563292021 @default.
- W2798956329 countsByYear W27989563292022 @default.
- W2798956329 countsByYear W27989563292023 @default.
- W2798956329 crossrefType "proceedings-article" @default.
- W2798956329 hasAuthorship W2798956329A5000839872 @default.
- W2798956329 hasAuthorship W2798956329A5019241553 @default.
- W2798956329 hasAuthorship W2798956329A5028650738 @default.
- W2798956329 hasAuthorship W2798956329A5034579434 @default.
- W2798956329 hasConcept C103278499 @default.
- W2798956329 hasConcept C108583219 @default.
- W2798956329 hasConcept C115961682 @default.
- W2798956329 hasConcept C133667856 @default.
- W2798956329 hasConcept C138111711 @default.
- W2798956329 hasConcept C153180895 @default.
- W2798956329 hasConcept C154945302 @default.
- W2798956329 hasConcept C1667742 @default.
- W2798956329 hasConcept C184898388 @default.
- W2798956329 hasConcept C22019652 @default.
- W2798956329 hasConcept C38652104 @default.
- W2798956329 hasConcept C41008148 @default.
- W2798956329 hasConcept C50644808 @default.
- W2798956329 hasConcept C67388219 @default.
- W2798956329 hasConcept C99138194 @default.
- W2798956329 hasConceptScore W2798956329C103278499 @default.
- W2798956329 hasConceptScore W2798956329C108583219 @default.
- W2798956329 hasConceptScore W2798956329C115961682 @default.
- W2798956329 hasConceptScore W2798956329C133667856 @default.
- W2798956329 hasConceptScore W2798956329C138111711 @default.
- W2798956329 hasConceptScore W2798956329C153180895 @default.
- W2798956329 hasConceptScore W2798956329C154945302 @default.
- W2798956329 hasConceptScore W2798956329C1667742 @default.
- W2798956329 hasConceptScore W2798956329C184898388 @default.
- W2798956329 hasConceptScore W2798956329C22019652 @default.
- W2798956329 hasConceptScore W2798956329C38652104 @default.
- W2798956329 hasConceptScore W2798956329C41008148 @default.
- W2798956329 hasConceptScore W2798956329C50644808 @default.
- W2798956329 hasConceptScore W2798956329C67388219 @default.
- W2798956329 hasConceptScore W2798956329C99138194 @default.
- W2798956329 hasLocation W27989563291 @default.
- W2798956329 hasOpenAccess W2798956329 @default.
- W2798956329 hasPrimaryLocation W27989563291 @default.
- W2798956329 hasRelatedWork W1999265394 @default.
- W2798956329 hasRelatedWork W2393006666 @default.
- W2798956329 hasRelatedWork W2508837377 @default.
- W2798956329 hasRelatedWork W2509140289 @default.
- W2798956329 hasRelatedWork W3087964089 @default.
- W2798956329 hasRelatedWork W3099385964 @default.
- W2798956329 hasRelatedWork W3158263601 @default.
- W2798956329 hasRelatedWork W3160969343 @default.
- W2798956329 hasRelatedWork W4285484072 @default.
- W2798956329 hasRelatedWork W4312454624 @default.
- W2798956329 isParatext "false" @default.
- W2798956329 isRetracted "false" @default.
- W2798956329 magId "2798956329" @default.
- W2798956329 workType "article" @default.