Matches in SemOpenAlex for { <https://semopenalex.org/work/W2990996919> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W2990996919 endingPage "107116" @default.
- W2990996919 startingPage "107116" @default.
- W2990996919 abstract "Abstract Hashing is one of the most promising techniques in approximate nearest neighbor search due to its time efficiency and low cost in memory. Recently, with the help of deep learning, deep supervised hashing can perform representation learning and compact hash code learning jointly in an end-to-end style, and obtains better retrieval accuracy compared to non-deep methods. However, most deep hashing methods are trained with a pair-wise loss or triplet loss in a mini-batch style, which makes them inefficient at data sampling and cannot preserve the global similarity information. Besides that, many existing methods generate hash codes with redundant or even harmful bits, which is a waste of space and may lower the retrieval accuracy. In this paper, we propose a novel deep reinforcement hashing model with redundancy elimination called Deep Reinforcement De-Redundancy Hashing (DRDH), which can fully exploit large-scale similarity information and eliminate redundant hash bits with deep reinforcement learning. DRDH conducts hash code inference in a block-wise style, and uses Deep Q Network (DQN) to eliminate redundant bits. Very promising results have been achieved on four public datasets, i.e., CIFAR-10, NUS-WIDE, MS-COCO, and Open-Images-V4, which demonstrate that our method can generate highly compact hash codes and yield better retrieval performance than those of state-of-the-art methods." @default.
- W2990996919 created "2019-12-05" @default.
- W2990996919 creator A5035701638 @default.
- W2990996919 creator A5038355224 @default.
- W2990996919 creator A5067518097 @default.
- W2990996919 creator A5070073283 @default.
- W2990996919 creator A5075964389 @default.
- W2990996919 date "2020-04-01" @default.
- W2990996919 modified "2023-10-17" @default.
- W2990996919 title "Deep reinforcement hashing with redundancy elimination for effective image retrieval" @default.
- W2990996919 cites W2079202281 @default.
- W2990996919 cites W2593190442 @default.
- W2990996919 cites W2599837009 @default.
- W2990996919 cites W2783286101 @default.
- W2990996919 cites W2791731057 @default.
- W2990996919 cites W2804165720 @default.
- W2990996919 cites W2890594753 @default.
- W2990996919 cites W2906146234 @default.
- W2990996919 doi "https://doi.org/10.1016/j.patcog.2019.107116" @default.
- W2990996919 hasPublicationYear "2020" @default.
- W2990996919 type Work @default.
- W2990996919 sameAs 2990996919 @default.
- W2990996919 citedByCount "12" @default.
- W2990996919 countsByYear W29909969192020 @default.
- W2990996919 countsByYear W29909969192021 @default.
- W2990996919 countsByYear W29909969192022 @default.
- W2990996919 crossrefType "journal-article" @default.
- W2990996919 hasAuthorship W2990996919A5035701638 @default.
- W2990996919 hasAuthorship W2990996919A5038355224 @default.
- W2990996919 hasAuthorship W2990996919A5067518097 @default.
- W2990996919 hasAuthorship W2990996919A5070073283 @default.
- W2990996919 hasAuthorship W2990996919A5075964389 @default.
- W2990996919 hasConcept C111919701 @default.
- W2990996919 hasConcept C115961682 @default.
- W2990996919 hasConcept C152124472 @default.
- W2990996919 hasConcept C153180895 @default.
- W2990996919 hasConcept C154945302 @default.
- W2990996919 hasConcept C1667742 @default.
- W2990996919 hasConcept C38652104 @default.
- W2990996919 hasConcept C41008148 @default.
- W2990996919 hasConcept C97541855 @default.
- W2990996919 hasConcept C99138194 @default.
- W2990996919 hasConceptScore W2990996919C111919701 @default.
- W2990996919 hasConceptScore W2990996919C115961682 @default.
- W2990996919 hasConceptScore W2990996919C152124472 @default.
- W2990996919 hasConceptScore W2990996919C153180895 @default.
- W2990996919 hasConceptScore W2990996919C154945302 @default.
- W2990996919 hasConceptScore W2990996919C1667742 @default.
- W2990996919 hasConceptScore W2990996919C38652104 @default.
- W2990996919 hasConceptScore W2990996919C41008148 @default.
- W2990996919 hasConceptScore W2990996919C97541855 @default.
- W2990996919 hasConceptScore W2990996919C99138194 @default.
- W2990996919 hasFunder F4320309612 @default.
- W2990996919 hasFunder F4320321001 @default.
- W2990996919 hasFunder F4320321885 @default.
- W2990996919 hasFunder F4320335982 @default.
- W2990996919 hasLocation W29909969191 @default.
- W2990996919 hasOpenAccess W2990996919 @default.
- W2990996919 hasPrimaryLocation W29909969191 @default.
- W2990996919 hasRelatedWork W2003020068 @default.
- W2990996919 hasRelatedWork W2130538965 @default.
- W2990996919 hasRelatedWork W2189043660 @default.
- W2990996919 hasRelatedWork W2352930817 @default.
- W2990996919 hasRelatedWork W2399159263 @default.
- W2990996919 hasRelatedWork W2612705911 @default.
- W2990996919 hasRelatedWork W2908044305 @default.
- W2990996919 hasRelatedWork W3027686766 @default.
- W2990996919 hasRelatedWork W3167466176 @default.
- W2990996919 hasRelatedWork W3202634820 @default.
- W2990996919 hasVolume "100" @default.
- W2990996919 isParatext "false" @default.
- W2990996919 isRetracted "false" @default.
- W2990996919 magId "2990996919" @default.
- W2990996919 workType "article" @default.