Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385804905> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4385804905 abstract "Constructing annotated paired datasets for low-light image enhancement is complex and time-consuming, and existing deep learning models often generate noisy outputs or misinterpret shadows. To effectively learn intricate relationships between features in image space with limited labels, we introduce a deep learning model with a backbone structure that incorporates both spatial and layer-wise dependencies. The proposed model features a baseline image-enhancing network with spatial dependencies and an optimized layer attention mechanism to learn feature sparsity and importance. We present a progressive supervised loss function for improvement. Furthermore, we propose a novel Multi-Consistency Regularization (MCR) loss and integrate it within a Multi-Consistency Mean Teacher (MCMT) framework, which enforces agreement on high-level features and incorporates intermediate features for better understanding of the entire image. By combining the MCR loss with the progressive supervised loss, student network parameters can be updated in a single step. Our approach achieves significant performance improvements using fewer labeled data and unlabeled low-light images within our semi-supervised framework. Qualitative evaluations demonstrate the effectiveness of our method in leveraging comprehensive dependencies and unlabeled data for low-light image enhancement." @default.
- W4385804905 created "2023-08-15" @default.
- W4385804905 creator A5008054386 @default.
- W4385804905 creator A5015627158 @default.
- W4385804905 creator A5081735317 @default.
- W4385804905 date "2023-06-01" @default.
- W4385804905 modified "2023-10-14" @default.
- W4385804905 title "Temporally Averaged Regression for Semi-Supervised Low-Light Image Enhancement" @default.
- W4385804905 cites W1976468890 @default.
- W4385804905 cites W1987444808 @default.
- W4385804905 cites W2001412060 @default.
- W4385804905 cites W2011260964 @default.
- W4385804905 cites W2054814429 @default.
- W4385804905 cites W2055745001 @default.
- W4385804905 cites W2076205488 @default.
- W4385804905 cites W2082195868 @default.
- W4385804905 cites W2116899452 @default.
- W4385804905 cites W2121900453 @default.
- W4385804905 cites W2133665775 @default.
- W4385804905 cites W2146439264 @default.
- W4385804905 cites W2150461190 @default.
- W4385804905 cites W2150721269 @default.
- W4385804905 cites W2254039850 @default.
- W4385804905 cites W2412926690 @default.
- W4385804905 cites W2566376500 @default.
- W4385804905 cites W2736326359 @default.
- W4385804905 cites W2752782242 @default.
- W4385804905 cites W2766802800 @default.
- W4385804905 cites W2783573276 @default.
- W4385804905 cites W2791710889 @default.
- W4385804905 cites W2948354154 @default.
- W4385804905 cites W2963228457 @default.
- W4385804905 cites W2981718299 @default.
- W4385804905 cites W3034347506 @default.
- W4385804905 doi "https://doi.org/10.1109/cvprw59228.2023.00443" @default.
- W4385804905 hasPublicationYear "2023" @default.
- W4385804905 type Work @default.
- W4385804905 citedByCount "0" @default.
- W4385804905 crossrefType "proceedings-article" @default.
- W4385804905 hasAuthorship W4385804905A5008054386 @default.
- W4385804905 hasAuthorship W4385804905A5015627158 @default.
- W4385804905 hasAuthorship W4385804905A5081735317 @default.
- W4385804905 hasConcept C105795698 @default.
- W4385804905 hasConcept C108583219 @default.
- W4385804905 hasConcept C111919701 @default.
- W4385804905 hasConcept C115961682 @default.
- W4385804905 hasConcept C119857082 @default.
- W4385804905 hasConcept C138885662 @default.
- W4385804905 hasConcept C153180895 @default.
- W4385804905 hasConcept C154945302 @default.
- W4385804905 hasConcept C2776135515 @default.
- W4385804905 hasConcept C2776401178 @default.
- W4385804905 hasConcept C2776436953 @default.
- W4385804905 hasConcept C33923547 @default.
- W4385804905 hasConcept C41008148 @default.
- W4385804905 hasConcept C41895202 @default.
- W4385804905 hasConcept C83546350 @default.
- W4385804905 hasConcept C93361087 @default.
- W4385804905 hasConceptScore W4385804905C105795698 @default.
- W4385804905 hasConceptScore W4385804905C108583219 @default.
- W4385804905 hasConceptScore W4385804905C111919701 @default.
- W4385804905 hasConceptScore W4385804905C115961682 @default.
- W4385804905 hasConceptScore W4385804905C119857082 @default.
- W4385804905 hasConceptScore W4385804905C138885662 @default.
- W4385804905 hasConceptScore W4385804905C153180895 @default.
- W4385804905 hasConceptScore W4385804905C154945302 @default.
- W4385804905 hasConceptScore W4385804905C2776135515 @default.
- W4385804905 hasConceptScore W4385804905C2776401178 @default.
- W4385804905 hasConceptScore W4385804905C2776436953 @default.
- W4385804905 hasConceptScore W4385804905C33923547 @default.
- W4385804905 hasConceptScore W4385804905C41008148 @default.
- W4385804905 hasConceptScore W4385804905C41895202 @default.
- W4385804905 hasConceptScore W4385804905C83546350 @default.
- W4385804905 hasConceptScore W4385804905C93361087 @default.
- W4385804905 hasLocation W43858049051 @default.
- W4385804905 hasOpenAccess W4385804905 @default.
- W4385804905 hasPrimaryLocation W43858049051 @default.
- W4385804905 hasRelatedWork W2353865532 @default.
- W4385804905 hasRelatedWork W3014300295 @default.
- W4385804905 hasRelatedWork W3164822677 @default.
- W4385804905 hasRelatedWork W4223943233 @default.
- W4385804905 hasRelatedWork W4225161397 @default.
- W4385804905 hasRelatedWork W4312200629 @default.
- W4385804905 hasRelatedWork W4360585206 @default.
- W4385804905 hasRelatedWork W4364306694 @default.
- W4385804905 hasRelatedWork W4380075502 @default.
- W4385804905 hasRelatedWork W4380086463 @default.
- W4385804905 isParatext "false" @default.
- W4385804905 isRetracted "false" @default.
- W4385804905 workType "article" @default.