Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308235698> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4308235698 abstract "Deep hashing aims to produce discriminative binary hash codes for fast image retrieval through a deep baseline network and additional trainable hash function. In a supervised deep hashing network, the baseline network is generally initialized with classification-based pretrained models, and the overall hashing network is trained in a supervised fashion. However, since classification and retrieval are two different tasks, it is necessary to reconsider the initial model for the baseline network. In this paper, we propose to use a self-supervised pretrained model as the baseline for the first time. We investigate the impact of pretrained model types by comparing deep hashing networks that use the baseline network with 1) randomly initialized weights, 2) conventional supervised pretrained weights, and 3) proposed self-supervised pretrained weights. As a result, we confirm that the performance of deep hashing differs depending on the initial baseline setting, and the proposed self-supervised baseline model shows comparable or better performance over the supervised one. Our code is released at https://github.com/HaeyoonYang/SSPH." @default.
- W4308235698 created "2022-11-09" @default.
- W4308235698 creator A5055171648 @default.
- W4308235698 creator A5069774986 @default.
- W4308235698 creator A5075209169 @default.
- W4308235698 creator A5081160754 @default.
- W4308235698 date "2022-10-16" @default.
- W4308235698 modified "2023-09-30" @default.
- W4308235698 title "Self-Supervised Pretraining for Deep Hash-Based Image Retrieval" @default.
- W4308235698 cites W2007972815 @default.
- W4308235698 cites W2108598243 @default.
- W4308235698 cites W2493727926 @default.
- W4308235698 cites W2508837377 @default.
- W4308235698 cites W2798834175 @default.
- W4308235698 cites W2964280870 @default.
- W4308235698 cites W2966218308 @default.
- W4308235698 cites W3025709990 @default.
- W4308235698 cites W3034239448 @default.
- W4308235698 cites W3159481202 @default.
- W4308235698 cites W4240805545 @default.
- W4308235698 doi "https://doi.org/10.1109/icip46576.2022.9897296" @default.
- W4308235698 hasPublicationYear "2022" @default.
- W4308235698 type Work @default.
- W4308235698 citedByCount "0" @default.
- W4308235698 crossrefType "proceedings-article" @default.
- W4308235698 hasAuthorship W4308235698A5055171648 @default.
- W4308235698 hasAuthorship W4308235698A5069774986 @default.
- W4308235698 hasAuthorship W4308235698A5075209169 @default.
- W4308235698 hasAuthorship W4308235698A5081160754 @default.
- W4308235698 hasConcept C108583219 @default.
- W4308235698 hasConcept C111368507 @default.
- W4308235698 hasConcept C115961682 @default.
- W4308235698 hasConcept C119857082 @default.
- W4308235698 hasConcept C12725497 @default.
- W4308235698 hasConcept C127313418 @default.
- W4308235698 hasConcept C153180895 @default.
- W4308235698 hasConcept C154945302 @default.
- W4308235698 hasConcept C1667742 @default.
- W4308235698 hasConcept C33923547 @default.
- W4308235698 hasConcept C38652104 @default.
- W4308235698 hasConcept C41008148 @default.
- W4308235698 hasConcept C48372109 @default.
- W4308235698 hasConcept C63435697 @default.
- W4308235698 hasConcept C94375191 @default.
- W4308235698 hasConcept C97931131 @default.
- W4308235698 hasConcept C99138194 @default.
- W4308235698 hasConceptScore W4308235698C108583219 @default.
- W4308235698 hasConceptScore W4308235698C111368507 @default.
- W4308235698 hasConceptScore W4308235698C115961682 @default.
- W4308235698 hasConceptScore W4308235698C119857082 @default.
- W4308235698 hasConceptScore W4308235698C12725497 @default.
- W4308235698 hasConceptScore W4308235698C127313418 @default.
- W4308235698 hasConceptScore W4308235698C153180895 @default.
- W4308235698 hasConceptScore W4308235698C154945302 @default.
- W4308235698 hasConceptScore W4308235698C1667742 @default.
- W4308235698 hasConceptScore W4308235698C33923547 @default.
- W4308235698 hasConceptScore W4308235698C38652104 @default.
- W4308235698 hasConceptScore W4308235698C41008148 @default.
- W4308235698 hasConceptScore W4308235698C48372109 @default.
- W4308235698 hasConceptScore W4308235698C63435697 @default.
- W4308235698 hasConceptScore W4308235698C94375191 @default.
- W4308235698 hasConceptScore W4308235698C97931131 @default.
- W4308235698 hasConceptScore W4308235698C99138194 @default.
- W4308235698 hasLocation W43082356981 @default.
- W4308235698 hasOpenAccess W4308235698 @default.
- W4308235698 hasPrimaryLocation W43082356981 @default.
- W4308235698 hasRelatedWork W2024160000 @default.
- W4308235698 hasRelatedWork W2729514902 @default.
- W4308235698 hasRelatedWork W2773500201 @default.
- W4308235698 hasRelatedWork W2984143580 @default.
- W4308235698 hasRelatedWork W2995523806 @default.
- W4308235698 hasRelatedWork W3025709990 @default.
- W4308235698 hasRelatedWork W4200200221 @default.
- W4308235698 hasRelatedWork W4225654135 @default.
- W4308235698 hasRelatedWork W4308235698 @default.
- W4308235698 hasRelatedWork W4380075502 @default.
- W4308235698 isParatext "false" @default.
- W4308235698 isRetracted "false" @default.
- W4308235698 workType "article" @default.