Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387444569> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4387444569 abstract "Learning a single underwater image enhancement network from unpaired degraded and clear images is of practical interest. In reality, it is almost infeasible to obtain clear reference images corresponding to captured images in the IoT underwater. As a result, training enhancement networks in a supervised manner is challenging in the absence of such paired data. At the same time, existing methods are often insufficient to learn the semantic and texture knowledge inherent in clear images from limited data due to the significant variability between clear and degraded image domains. In response, we propose a two-branch contrast enhancement framework (DCE-Net) for unpaired underwater image enhancement, which learns mutual information between clear and degraded image domains from a limited amount of unpaired data. The proposed DCE-Net consists of a Cyclic Consistency Module (CCM) and a Contrast Enhancement Module (CEM). Specifically, the CCM is designed to guide feature transformation and latent feature learning between underwater clear images and underwater degraded images. the CEM is designed to constrain the consistency of semantic information between underwater clear images and underwater degraded images, encouraging better enhancement and improving image recovery quality. Extensive experiments are conducted using publicly available underwater datasets. The results demonstrate the effectiveness of the proposed method." @default.
- W4387444569 created "2023-10-10" @default.
- W4387444569 creator A5053156190 @default.
- W4387444569 creator A5058413717 @default.
- W4387444569 date "2023-07-27" @default.
- W4387444569 modified "2023-10-11" @default.
- W4387444569 title "Dual-branch Contrastive Learning for Image Enhancement of Underwater Internet of Things" @default.
- W4387444569 cites W2763503841 @default.
- W4387444569 cites W2892845027 @default.
- W4387444569 cites W2948400274 @default.
- W4387444569 cites W2956328874 @default.
- W4387444569 cites W2962793481 @default.
- W4387444569 cites W2971483169 @default.
- W4387444569 cites W2990176100 @default.
- W4387444569 cites W2997763120 @default.
- W4387444569 cites W3006777311 @default.
- W4387444569 cites W3028921661 @default.
- W4387444569 cites W3042930711 @default.
- W4387444569 cites W3195744835 @default.
- W4387444569 cites W4200606162 @default.
- W4387444569 cites W4226197550 @default.
- W4387444569 cites W4240805545 @default.
- W4387444569 cites W4283521894 @default.
- W4387444569 cites W4313128106 @default.
- W4387444569 cites W4327662929 @default.
- W4387444569 doi "https://doi.org/10.1109/icivc58118.2023.10270633" @default.
- W4387444569 hasPublicationYear "2023" @default.
- W4387444569 type Work @default.
- W4387444569 citedByCount "0" @default.
- W4387444569 crossrefType "proceedings-article" @default.
- W4387444569 hasAuthorship W4387444569A5053156190 @default.
- W4387444569 hasAuthorship W4387444569A5058413717 @default.
- W4387444569 hasConcept C111368507 @default.
- W4387444569 hasConcept C115961682 @default.
- W4387444569 hasConcept C127313418 @default.
- W4387444569 hasConcept C138885662 @default.
- W4387444569 hasConcept C153180895 @default.
- W4387444569 hasConcept C154945302 @default.
- W4387444569 hasConcept C2776401178 @default.
- W4387444569 hasConcept C2776436953 @default.
- W4387444569 hasConcept C2776502983 @default.
- W4387444569 hasConcept C31972630 @default.
- W4387444569 hasConcept C41008148 @default.
- W4387444569 hasConcept C41895202 @default.
- W4387444569 hasConcept C55020928 @default.
- W4387444569 hasConcept C98083399 @default.
- W4387444569 hasConceptScore W4387444569C111368507 @default.
- W4387444569 hasConceptScore W4387444569C115961682 @default.
- W4387444569 hasConceptScore W4387444569C127313418 @default.
- W4387444569 hasConceptScore W4387444569C138885662 @default.
- W4387444569 hasConceptScore W4387444569C153180895 @default.
- W4387444569 hasConceptScore W4387444569C154945302 @default.
- W4387444569 hasConceptScore W4387444569C2776401178 @default.
- W4387444569 hasConceptScore W4387444569C2776436953 @default.
- W4387444569 hasConceptScore W4387444569C2776502983 @default.
- W4387444569 hasConceptScore W4387444569C31972630 @default.
- W4387444569 hasConceptScore W4387444569C41008148 @default.
- W4387444569 hasConceptScore W4387444569C41895202 @default.
- W4387444569 hasConceptScore W4387444569C55020928 @default.
- W4387444569 hasConceptScore W4387444569C98083399 @default.
- W4387444569 hasFunder F4320321001 @default.
- W4387444569 hasLocation W43874445691 @default.
- W4387444569 hasOpenAccess W4387444569 @default.
- W4387444569 hasPrimaryLocation W43874445691 @default.
- W4387444569 hasRelatedWork W1600803092 @default.
- W4387444569 hasRelatedWork W1999583034 @default.
- W4387444569 hasRelatedWork W2773822314 @default.
- W4387444569 hasRelatedWork W2895964774 @default.
- W4387444569 hasRelatedWork W2910761503 @default.
- W4387444569 hasRelatedWork W2953138830 @default.
- W4387444569 hasRelatedWork W3168963531 @default.
- W4387444569 hasRelatedWork W3176162126 @default.
- W4387444569 hasRelatedWork W3201231642 @default.
- W4387444569 hasRelatedWork W3217214504 @default.
- W4387444569 isParatext "false" @default.
- W4387444569 isRetracted "false" @default.
- W4387444569 workType "article" @default.