Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382458598> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4382458598 endingPage "3686" @default.
- W4382458598 startingPage "3678" @default.
- W4382458598 abstract "Low-light images suffer severe degradation of low lightness and noise corruption, causing unsatisfactory visual quality and visual recognition performance. To solve this problem while meeting the unavailability of paired datasets in wide-range scenarios, unsupervised low-light image enhancement (ULLIE) techniques have been developed. However, these methods are primarily guided to alleviate the degradation effect on visual quality rather than semantic levels, hence limiting their performance in visual recognition tasks. To this end, we propose to learn a Semantic Degradation-Aware Guidance (SDAG) that perceives the low-light degradation effect on semantic levels in a self-supervised manner, which is further utilized to guide the ULLIE methods. The proposed SDAG utilizes the low-light degradation factors as augmented signals to degrade the low-light images, and then capture their degradation effect on semantic levels. Specifically, our SDAG employs the subsequent pre-trained recognition model extractor to extract semantic representations, and then learns to self-reconstruct the enhanced low-light image and its augmented degraded images. By constraining the relative reconstruction effect between the original enhanced image and the augmented formats, our SDAG learns to be aware of the degradation effect on semantic levels in a relative comparison manner. Moreover, our SDAG is general and can be plugged into the training paradigm of the existing ULLIE methods. Extensive experiments demonstrate its effectiveness for improving the ULLIE approaches on the downstream recognition tasks while maintaining a competitive visual quality. Code will be available at https://github.com/zheng980629/SDAG." @default.
- W4382458598 created "2023-06-29" @default.
- W4382458598 creator A5005310183 @default.
- W4382458598 creator A5048814096 @default.
- W4382458598 creator A5052274720 @default.
- W4382458598 creator A5062166339 @default.
- W4382458598 creator A5072972309 @default.
- W4382458598 creator A5090160917 @default.
- W4382458598 date "2023-06-26" @default.
- W4382458598 modified "2023-09-27" @default.
- W4382458598 title "Learning Semantic Degradation-Aware Guidance for Recognition-Driven Unsupervised Low-Light Image Enhancement" @default.
- W4382458598 doi "https://doi.org/10.1609/aaai.v37i3.25479" @default.
- W4382458598 hasPublicationYear "2023" @default.
- W4382458598 type Work @default.
- W4382458598 citedByCount "0" @default.
- W4382458598 crossrefType "journal-article" @default.
- W4382458598 hasAuthorship W4382458598A5005310183 @default.
- W4382458598 hasAuthorship W4382458598A5048814096 @default.
- W4382458598 hasAuthorship W4382458598A5052274720 @default.
- W4382458598 hasAuthorship W4382458598A5062166339 @default.
- W4382458598 hasAuthorship W4382458598A5072972309 @default.
- W4382458598 hasAuthorship W4382458598A5090160917 @default.
- W4382458598 hasBestOaLocation W43824585981 @default.
- W4382458598 hasConcept C127413603 @default.
- W4382458598 hasConcept C153180895 @default.
- W4382458598 hasConcept C154945302 @default.
- W4382458598 hasConcept C200601418 @default.
- W4382458598 hasConcept C2779679103 @default.
- W4382458598 hasConcept C2780505938 @default.
- W4382458598 hasConcept C31972630 @default.
- W4382458598 hasConcept C41008148 @default.
- W4382458598 hasConcept C76155785 @default.
- W4382458598 hasConceptScore W4382458598C127413603 @default.
- W4382458598 hasConceptScore W4382458598C153180895 @default.
- W4382458598 hasConceptScore W4382458598C154945302 @default.
- W4382458598 hasConceptScore W4382458598C200601418 @default.
- W4382458598 hasConceptScore W4382458598C2779679103 @default.
- W4382458598 hasConceptScore W4382458598C2780505938 @default.
- W4382458598 hasConceptScore W4382458598C31972630 @default.
- W4382458598 hasConceptScore W4382458598C41008148 @default.
- W4382458598 hasConceptScore W4382458598C76155785 @default.
- W4382458598 hasIssue "3" @default.
- W4382458598 hasLocation W43824585981 @default.
- W4382458598 hasOpenAccess W4382458598 @default.
- W4382458598 hasPrimaryLocation W43824585981 @default.
- W4382458598 hasRelatedWork W1841747458 @default.
- W4382458598 hasRelatedWork W1891287906 @default.
- W4382458598 hasRelatedWork W1969923398 @default.
- W4382458598 hasRelatedWork W2036807459 @default.
- W4382458598 hasRelatedWork W2166024367 @default.
- W4382458598 hasRelatedWork W2229312674 @default.
- W4382458598 hasRelatedWork W2755342338 @default.
- W4382458598 hasRelatedWork W2772917594 @default.
- W4382458598 hasRelatedWork W2909609266 @default.
- W4382458598 hasRelatedWork W3116076068 @default.
- W4382458598 hasVolume "37" @default.
- W4382458598 isParatext "false" @default.
- W4382458598 isRetracted "false" @default.
- W4382458598 workType "article" @default.