Matches in SemOpenAlex for { <https://semopenalex.org/work/W3159483217> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W3159483217 abstract "Recently, deep convolutional neural networks (DCNN) that leverage the adversarial training framework for image restoration and enhancement have significantly improved the processed images' sharpness. Surprisingly, although these DCNNs produced crispier images than other methods visually, they may get a lower quality score when popular measures are employed for evaluating them. Therefore it is necessary to develop a quantitative metric to reflect their performances, which is well-aligned with the perceived quality of an image. Famous quantitative metrics such as Peak signal-to-noise ratio (PSNR), The structural similarity index measure (SSIM), and Perceptual Index (PI) are not well-correlated with the mean opinion score (MOS) for an image, especially for the neural networks trained with adversarial loss functions. This paper has proposed a convolutional neural network using an extension architecture of the traditional Siamese network so-called Siamese-Difference neural network. We have equipped this architecture with the spatial and channel-wise attention mechanism to increase our method's performance. Finally, we employed an auxiliary loss function to train our model. The suggested additional cost function surrogates ranking loss to increase Spearman's rank correlation coefficient while it is differentiable concerning the neural network parameters. Our method achieved superior performance in textbf{textit{NTIRE 2021 Perceptual Image Quality Assessment}} Challenge. The implementations of our proposed method are publicly available." @default.
- W3159483217 created "2021-05-10" @default.
- W3159483217 creator A5009390373 @default.
- W3159483217 creator A5036848175 @default.
- W3159483217 date "2021-06-01" @default.
- W3159483217 modified "2023-10-14" @default.
- W3159483217 title "(ASNA) An Attention-based Siamese-Difference Neural Network with Surrogate Ranking Loss function for Perceptual Image Quality Assessment" @default.
- W3159483217 cites W1580389772 @default.
- W3159483217 cites W1972006393 @default.
- W3159483217 cites W1974013408 @default.
- W3159483217 cites W1984553492 @default.
- W3159483217 cites W2009272644 @default.
- W3159483217 cites W2015196405 @default.
- W3159483217 cites W2046119925 @default.
- W3159483217 cites W2064076387 @default.
- W3159483217 cites W2067921844 @default.
- W3159483217 cites W2102166818 @default.
- W3159483217 cites W2133665775 @default.
- W3159483217 cites W2141983208 @default.
- W3159483217 cites W2142884912 @default.
- W3159483217 cites W2144468361 @default.
- W3159483217 cites W2152059677 @default.
- W3159483217 cites W2159269332 @default.
- W3159483217 cites W2161907179 @default.
- W3159483217 cites W2171349048 @default.
- W3159483217 cites W2565312867 @default.
- W3159483217 cites W2768814045 @default.
- W3159483217 cites W2798581339 @default.
- W3159483217 cites W2891248708 @default.
- W3159483217 cites W2898910409 @default.
- W3159483217 cites W2962785568 @default.
- W3159483217 cites W2963372104 @default.
- W3159483217 cites W2982693525 @default.
- W3159483217 cites W3100498948 @default.
- W3159483217 cites W3102564565 @default.
- W3159483217 cites W577825744 @default.
- W3159483217 doi "https://doi.org/10.1109/cvprw53098.2021.00049" @default.
- W3159483217 hasPublicationYear "2021" @default.
- W3159483217 type Work @default.
- W3159483217 sameAs 3159483217 @default.
- W3159483217 citedByCount "5" @default.
- W3159483217 countsByYear W31594832172022 @default.
- W3159483217 crossrefType "proceedings-article" @default.
- W3159483217 hasAuthorship W3159483217A5009390373 @default.
- W3159483217 hasAuthorship W3159483217A5036848175 @default.
- W3159483217 hasBestOaLocation W31594832172 @default.
- W3159483217 hasConcept C115961682 @default.
- W3159483217 hasConcept C119857082 @default.
- W3159483217 hasConcept C127413603 @default.
- W3159483217 hasConcept C153083717 @default.
- W3159483217 hasConcept C153180895 @default.
- W3159483217 hasConcept C154945302 @default.
- W3159483217 hasConcept C15744967 @default.
- W3159483217 hasConcept C169760540 @default.
- W3159483217 hasConcept C176217482 @default.
- W3159483217 hasConcept C189430467 @default.
- W3159483217 hasConcept C21547014 @default.
- W3159483217 hasConcept C26760741 @default.
- W3159483217 hasConcept C2779346075 @default.
- W3159483217 hasConcept C41008148 @default.
- W3159483217 hasConcept C50644808 @default.
- W3159483217 hasConcept C55020928 @default.
- W3159483217 hasConcept C62897895 @default.
- W3159483217 hasConcept C81363708 @default.
- W3159483217 hasConceptScore W3159483217C115961682 @default.
- W3159483217 hasConceptScore W3159483217C119857082 @default.
- W3159483217 hasConceptScore W3159483217C127413603 @default.
- W3159483217 hasConceptScore W3159483217C153083717 @default.
- W3159483217 hasConceptScore W3159483217C153180895 @default.
- W3159483217 hasConceptScore W3159483217C154945302 @default.
- W3159483217 hasConceptScore W3159483217C15744967 @default.
- W3159483217 hasConceptScore W3159483217C169760540 @default.
- W3159483217 hasConceptScore W3159483217C176217482 @default.
- W3159483217 hasConceptScore W3159483217C189430467 @default.
- W3159483217 hasConceptScore W3159483217C21547014 @default.
- W3159483217 hasConceptScore W3159483217C26760741 @default.
- W3159483217 hasConceptScore W3159483217C2779346075 @default.
- W3159483217 hasConceptScore W3159483217C41008148 @default.
- W3159483217 hasConceptScore W3159483217C50644808 @default.
- W3159483217 hasConceptScore W3159483217C55020928 @default.
- W3159483217 hasConceptScore W3159483217C62897895 @default.
- W3159483217 hasConceptScore W3159483217C81363708 @default.
- W3159483217 hasLocation W31594832171 @default.
- W3159483217 hasLocation W31594832172 @default.
- W3159483217 hasOpenAccess W3159483217 @default.
- W3159483217 hasPrimaryLocation W31594832171 @default.
- W3159483217 hasRelatedWork W2526960468 @default.
- W3159483217 hasRelatedWork W2726083349 @default.
- W3159483217 hasRelatedWork W2751066217 @default.
- W3159483217 hasRelatedWork W2955938200 @default.
- W3159483217 hasRelatedWork W3109429904 @default.
- W3159483217 hasRelatedWork W4220798441 @default.
- W3159483217 hasRelatedWork W4221002337 @default.
- W3159483217 hasRelatedWork W4221158116 @default.
- W3159483217 hasRelatedWork W4313330642 @default.
- W3159483217 hasRelatedWork W2004336531 @default.
- W3159483217 isParatext "false" @default.
- W3159483217 isRetracted "false" @default.
- W3159483217 magId "3159483217" @default.
- W3159483217 workType "article" @default.