FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312286465> ?p ?o ?g. }

• W4312286465 abstract "Full-reference (FR) image quality assessment (IQA) evaluates the visual quality of a distorted image by measuring its perceptual difference with pristine-quality reference, and has been widely used in low-level vision tasks. Pairwise labeled data with mean opinion score (MOS) are required in training FR-IQA model, but is time-consuming and cumbersome to collect. In contrast, unlabeled data can be easily collected from an image degradation or restoration process, making it encouraging to exploit unlabeled training data to boost FR-IQA performance. Moreover, due to the distribution inconsistency between labeled and unlabeled data, outliers may occur in unlabeled data, further increasing the training difficulty. In this paper, we suggest to incorporate semi-supervised and positive-unlabeled (PU) learning for exploiting unlabeled data while mitigating the adverse effect of outliers. Particularly, by treating all labeled data as positive samples, PU learning is leveraged to identify negative samples (i.e., outliers) from unlabeled data. Semi-supervised learning (SSL) is further deployed to exploit positive unlabeled data by dynamically generating pseudo-MOS. We adopt a dual-branch network including reference and distortion branches. Furthermore, spatial attention is introduced in the reference branch to concentrate more on the informative regions, and sliced Wasserstein distance is used for robust difference map computation to address the misalignment issues caused by images recovered by GAN models. Extensive experiments show that our method performs favorably against state-of-the-arts on the benchmark datasets PIPAL, KADID-10k, TID2013, LIVE and CSIQ. The source code and model are available at https://github.com/happycaoyue/JSPL." @default.
• W4312286465 created "2023-01-04" @default.
• W4312286465 creator A5011577651 @default.
• W4312286465 creator A5018318136 @default.
• W4312286465 creator A5023241019 @default.
• W4312286465 creator A5028650738 @default.
• W4312286465 creator A5051402211 @default.
• W4312286465 date "2022-06-01" @default.
• W4312286465 modified "2023-10-16" @default.
• W4312286465 title "Incorporating Semi-Supervised and Positive-Unlabeled Learning for Boosting Full Reference Image Quality Assessment" @default.
• W4312286465 cites W1580389772 @default.
• W4312286465 cites W1937026393 @default.
• W4312286465 cites W1974013408 @default.
• W4312286465 cites W1977246677 @default.
• W4312286465 cites W1982471090 @default.
• W4312286465 cites W1982957666 @default.
• W4312286465 cites W2009272644 @default.
• W4312286465 cites W2015196405 @default.
• W4312286465 cites W2046119925 @default.
• W4312286465 cites W2049579898 @default.
• W4312286465 cites W2051596736 @default.
• W4312286465 cites W2052287864 @default.
• W4312286465 cites W2067921844 @default.
• W4312286465 cites W2102166818 @default.
• W4312286465 cites W2114582993 @default.
• W4312286465 cites W2133665775 @default.
• W4312286465 cites W2141983208 @default.
• W4312286465 cites W2142884912 @default.
• W4312286465 cites W2144468361 @default.
• W4312286465 cites W2151035455 @default.
• W4312286465 cites W2152059677 @default.
• W4312286465 cites W2159269332 @default.
• W4312286465 cites W2171349048 @default.
• W4312286465 cites W2473697052 @default.
• W4312286465 cites W2565312867 @default.
• W4312286465 cites W2566149141 @default.
• W4312286465 cites W2586275201 @default.
• W4312286465 cites W2618530766 @default.
• W4312286465 cites W2739757502 @default.
• W4312286465 cites W2741137940 @default.
• W4312286465 cites W2766716602 @default.
• W4312286465 cites W2767836774 @default.
• W4312286465 cites W2798581339 @default.
• W4312286465 cites W2905544033 @default.
• W4312286465 cites W2953590133 @default.
• W4312286465 cites W2962785568 @default.
• W4312286465 cites W2963918210 @default.
• W4312286465 cites W2964060609 @default.
• W4312286465 cites W3013773197 @default.
• W4312286465 cites W3017136408 @default.
• W4312286465 cites W3034504121 @default.
• W4312286465 cites W3035060634 @default.
• W4312286465 cites W3035719652 @default.
• W4312286465 cites W3036239693 @default.
• W4312286465 cites W3092515963 @default.
• W4312286465 cites W3098517161 @default.
• W4312286465 cites W3100498948 @default.
• W4312286465 cites W3159483217 @default.
• W4312286465 cites W3173515046 @default.
• W4312286465 cites W3174760001 @default.
• W4312286465 cites W3175356275 @default.
• W4312286465 cites W3175517129 @default.
• W4312286465 cites W3176592254 @default.
• W4312286465 cites W3176622443 @default.
• W4312286465 cites W3179365255 @default.
• W4312286465 doi "https://doi.org/10.1109/cvpr52688.2022.00576" @default.
• W4312286465 hasPublicationYear "2022" @default.
• W4312286465 type Work @default.
• W4312286465 citedByCount "1" @default.
• W4312286465 countsByYear W43122864652023 @default.
• W4312286465 crossrefType "proceedings-article" @default.
• W4312286465 hasAuthorship W4312286465A5011577651 @default.
• W4312286465 hasAuthorship W4312286465A5018318136 @default.
• W4312286465 hasAuthorship W4312286465A5023241019 @default.
• W4312286465 hasAuthorship W4312286465A5028650738 @default.
• W4312286465 hasAuthorship W4312286465A5051402211 @default.
• W4312286465 hasBestOaLocation W43122864652 @default.
• W4312286465 hasConcept C119857082 @default.
• W4312286465 hasConcept C126780896 @default.
• W4312286465 hasConcept C13280743 @default.
• W4312286465 hasConcept C153180895 @default.
• W4312286465 hasConcept C154945302 @default.
• W4312286465 hasConcept C162324750 @default.
• W4312286465 hasConcept C165696696 @default.
• W4312286465 hasConcept C176217482 @default.
• W4312286465 hasConcept C184898388 @default.
• W4312286465 hasConcept C185798385 @default.
• W4312286465 hasConcept C194257627 @default.
• W4312286465 hasConcept C205649164 @default.
• W4312286465 hasConcept C21547014 @default.
• W4312286465 hasConcept C24756922 @default.
• W4312286465 hasConcept C2776145971 @default.
• W4312286465 hasConcept C2776257435 @default.
• W4312286465 hasConcept C31258907 @default.
• W4312286465 hasConcept C38652104 @default.
• W4312286465 hasConcept C41008148 @default.
• W4312286465 hasConcept C42199009 @default.
• W4312286465 hasConcept C46686674 @default.
• W4312286465 hasConcept C79337645 @default.
• W4312286465 hasConceptScore W4312286465C119857082 @default.

• next