Matches in SemOpenAlex for { <https://semopenalex.org/work/W4324119488> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4324119488 abstract "Images captured under poor illumination suffer from poor visibility and weak information. The majority of low-light image enhancement (LLIE) methods are based on convolutional neural networks (CNNs), which leads to their inability to establish long-range context interaction. In this paper, we take the advantages of the Swin Transformer and ResNet to develop the Swin Transformer-based unsupervised Generative Adversarial Network (STUN) for the LLIE task. The STUN contains one generator and one discriminator. The generator includes modules for feature extraction, deep feature processing and image reconstruction. In particular, we use Swin Transformer blocks and ResNet in the deep feature processing module alternately to calculate the global and local attention. The self-feature preserving loss and the spatial consistency loss are employed to constrain the unsupervised learning of STUN. Experimental results on several low-light datasets indicate that STUN can achieve great performance in both visual quality and evaluation metrics." @default.
- W4324119488 created "2023-03-15" @default.
- W4324119488 creator A5003559530 @default.
- W4324119488 creator A5017360345 @default.
- W4324119488 creator A5021383194 @default.
- W4324119488 creator A5087244134 @default.
- W4324119488 date "2022-11-25" @default.
- W4324119488 modified "2023-10-16" @default.
- W4324119488 title "Swin Transformer based Unsupervised Network for Low-Light Image Enhancement" @default.
- W4324119488 cites W2102166818 @default.
- W4324119488 cites W2133665775 @default.
- W4324119488 cites W2194775991 @default.
- W4324119488 cites W2468596194 @default.
- W4324119488 cites W2566376500 @default.
- W4324119488 cites W2593414223 @default.
- W4324119488 cites W2963073614 @default.
- W4324119488 cites W2981718299 @default.
- W4324119488 cites W3035731588 @default.
- W4324119488 cites W3119525307 @default.
- W4324119488 cites W3120540810 @default.
- W4324119488 cites W3121661546 @default.
- W4324119488 cites W3138516171 @default.
- W4324119488 cites W3174792937 @default.
- W4324119488 cites W3207918547 @default.
- W4324119488 doi "https://doi.org/10.1109/cac57257.2022.10055781" @default.
- W4324119488 hasPublicationYear "2022" @default.
- W4324119488 type Work @default.
- W4324119488 citedByCount "0" @default.
- W4324119488 crossrefType "proceedings-article" @default.
- W4324119488 hasAuthorship W4324119488A5003559530 @default.
- W4324119488 hasAuthorship W4324119488A5017360345 @default.
- W4324119488 hasAuthorship W4324119488A5021383194 @default.
- W4324119488 hasAuthorship W4324119488A5087244134 @default.
- W4324119488 hasConcept C119599485 @default.
- W4324119488 hasConcept C127413603 @default.
- W4324119488 hasConcept C138885662 @default.
- W4324119488 hasConcept C153180895 @default.
- W4324119488 hasConcept C154945302 @default.
- W4324119488 hasConcept C165801399 @default.
- W4324119488 hasConcept C2776401178 @default.
- W4324119488 hasConcept C2779803651 @default.
- W4324119488 hasConcept C31972630 @default.
- W4324119488 hasConcept C41008148 @default.
- W4324119488 hasConcept C41895202 @default.
- W4324119488 hasConcept C52622490 @default.
- W4324119488 hasConcept C59404180 @default.
- W4324119488 hasConcept C66322947 @default.
- W4324119488 hasConcept C76155785 @default.
- W4324119488 hasConcept C8038995 @default.
- W4324119488 hasConcept C81363708 @default.
- W4324119488 hasConcept C94915269 @default.
- W4324119488 hasConceptScore W4324119488C119599485 @default.
- W4324119488 hasConceptScore W4324119488C127413603 @default.
- W4324119488 hasConceptScore W4324119488C138885662 @default.
- W4324119488 hasConceptScore W4324119488C153180895 @default.
- W4324119488 hasConceptScore W4324119488C154945302 @default.
- W4324119488 hasConceptScore W4324119488C165801399 @default.
- W4324119488 hasConceptScore W4324119488C2776401178 @default.
- W4324119488 hasConceptScore W4324119488C2779803651 @default.
- W4324119488 hasConceptScore W4324119488C31972630 @default.
- W4324119488 hasConceptScore W4324119488C41008148 @default.
- W4324119488 hasConceptScore W4324119488C41895202 @default.
- W4324119488 hasConceptScore W4324119488C52622490 @default.
- W4324119488 hasConceptScore W4324119488C59404180 @default.
- W4324119488 hasConceptScore W4324119488C66322947 @default.
- W4324119488 hasConceptScore W4324119488C76155785 @default.
- W4324119488 hasConceptScore W4324119488C8038995 @default.
- W4324119488 hasConceptScore W4324119488C81363708 @default.
- W4324119488 hasConceptScore W4324119488C94915269 @default.
- W4324119488 hasFunder F4320321001 @default.
- W4324119488 hasFunder F4320324852 @default.
- W4324119488 hasLocation W43241194881 @default.
- W4324119488 hasOpenAccess W4324119488 @default.
- W4324119488 hasPrimaryLocation W43241194881 @default.
- W4324119488 hasRelatedWork W2997229301 @default.
- W4324119488 hasRelatedWork W3167013339 @default.
- W4324119488 hasRelatedWork W3174759195 @default.
- W4324119488 hasRelatedWork W3213069564 @default.
- W4324119488 hasRelatedWork W4287121366 @default.
- W4324119488 hasRelatedWork W4308619659 @default.
- W4324119488 hasRelatedWork W4309346246 @default.
- W4324119488 hasRelatedWork W4386437125 @default.
- W4324119488 hasRelatedWork W4387323465 @default.
- W4324119488 hasRelatedWork W60493759 @default.
- W4324119488 isParatext "false" @default.
- W4324119488 isRetracted "false" @default.
- W4324119488 workType "article" @default.