Matches in SemOpenAlex for { <https://semopenalex.org/work/W3090791806> ?p ?o ?g. }
- W3090791806 abstract "In recent years, deep learning-based methods have been successfully applied to the image distortion restoration tasks. However, scenarios that assume a single distortion only may not be suitable for many real-world applications. To deal with such cases, some studies have proposed sequentially combined distortions datasets. Viewing in a different point of combining, we introduce a spatially-heterogeneous distortion dataset in which multiple corruptions are applied to the different locations of each image. In addition, we also propose a mixture of experts network to effectively restore a multi-distortion image. Motivated by the multi-task learning, we design our network to have multiple paths that learn both common and distortion-specific representations. Our model is effective for restoring real-world distortions and we experimentally verify that our method outperforms other models designed to manage both single distortion and multiple distortions." @default.
- W3090791806 created "2020-10-08" @default.
- W3090791806 creator A5047656074 @default.
- W3090791806 creator A5062357712 @default.
- W3090791806 creator A5068333871 @default.
- W3090791806 date "2020-09-30" @default.
- W3090791806 modified "2023-10-16" @default.
- W3090791806 title "Restoring Spatially-Heterogeneous Distortions using Mixture of Experts Network" @default.
- W3090791806 cites W1522301498 @default.
- W3090791806 cites W1677182931 @default.
- W3090791806 cites W1861492603 @default.
- W3090791806 cites W1885185971 @default.
- W3090791806 cites W1974013408 @default.
- W3090791806 cites W2015159529 @default.
- W3090791806 cites W2037642501 @default.
- W3090791806 cites W2056370875 @default.
- W3090791806 cites W2130184048 @default.
- W3090791806 cites W2150884987 @default.
- W3090791806 cites W2164603270 @default.
- W3090791806 cites W2194775991 @default.
- W3090791806 cites W2242218935 @default.
- W3090791806 cites W2503339013 @default.
- W3090791806 cites W2508457857 @default.
- W3090791806 cites W2531915888 @default.
- W3090791806 cites W2560533888 @default.
- W3090791806 cites W2607041014 @default.
- W3090791806 cites W2613718673 @default.
- W3090791806 cites W2624871570 @default.
- W3090791806 cites W2741137940 @default.
- W3090791806 cites W2747675701 @default.
- W3090791806 cites W2780544323 @default.
- W3090791806 cites W2798735168 @default.
- W3090791806 cites W2809290718 @default.
- W3090791806 cites W2866634454 @default.
- W3090791806 cites W2884585870 @default.
- W3090791806 cites W2905878277 @default.
- W3090791806 cites W2913340405 @default.
- W3090791806 cites W2941471678 @default.
- W3090791806 cites W2952323569 @default.
- W3090791806 cites W2955442343 @default.
- W3090791806 cites W2962419217 @default.
- W3090791806 cites W2962785568 @default.
- W3090791806 cites W2963150697 @default.
- W3090791806 cites W2963312584 @default.
- W3090791806 cites W2963372104 @default.
- W3090791806 cites W2963420686 @default.
- W3090791806 cites W2963470893 @default.
- W3090791806 cites W2963645458 @default.
- W3090791806 cites W2963653779 @default.
- W3090791806 cites W2963725279 @default.
- W3090791806 cites W2964268638 @default.
- W3090791806 cites W2964297221 @default.
- W3090791806 cites W2964343197 @default.
- W3090791806 cites W2983315964 @default.
- W3090791806 cites W2987150909 @default.
- W3090791806 cites W3001778788 @default.
- W3090791806 cites W3034938110 @default.
- W3090791806 cites W3104725225 @default.
- W3090791806 cites W54257720 @default.
- W3090791806 doi "https://doi.org/10.48550/arxiv.2009.14563" @default.
- W3090791806 hasPublicationYear "2020" @default.
- W3090791806 type Work @default.
- W3090791806 sameAs 3090791806 @default.
- W3090791806 citedByCount "0" @default.
- W3090791806 crossrefType "posted-content" @default.
- W3090791806 hasAuthorship W3090791806A5047656074 @default.
- W3090791806 hasAuthorship W3090791806A5062357712 @default.
- W3090791806 hasAuthorship W3090791806A5068333871 @default.
- W3090791806 hasBestOaLocation W30907918061 @default.
- W3090791806 hasConcept C115961682 @default.
- W3090791806 hasConcept C119857082 @default.
- W3090791806 hasConcept C124101348 @default.
- W3090791806 hasConcept C126780896 @default.
- W3090791806 hasConcept C127413603 @default.
- W3090791806 hasConcept C153180895 @default.
- W3090791806 hasConcept C154945302 @default.
- W3090791806 hasConcept C194257627 @default.
- W3090791806 hasConcept C201995342 @default.
- W3090791806 hasConcept C2524010 @default.
- W3090791806 hasConcept C2776257435 @default.
- W3090791806 hasConcept C2780451532 @default.
- W3090791806 hasConcept C28719098 @default.
- W3090791806 hasConcept C31258907 @default.
- W3090791806 hasConcept C31972630 @default.
- W3090791806 hasConcept C33923547 @default.
- W3090791806 hasConcept C41008148 @default.
- W3090791806 hasConceptScore W3090791806C115961682 @default.
- W3090791806 hasConceptScore W3090791806C119857082 @default.
- W3090791806 hasConceptScore W3090791806C124101348 @default.
- W3090791806 hasConceptScore W3090791806C126780896 @default.
- W3090791806 hasConceptScore W3090791806C127413603 @default.
- W3090791806 hasConceptScore W3090791806C153180895 @default.
- W3090791806 hasConceptScore W3090791806C154945302 @default.
- W3090791806 hasConceptScore W3090791806C194257627 @default.
- W3090791806 hasConceptScore W3090791806C201995342 @default.
- W3090791806 hasConceptScore W3090791806C2524010 @default.
- W3090791806 hasConceptScore W3090791806C2776257435 @default.
- W3090791806 hasConceptScore W3090791806C2780451532 @default.
- W3090791806 hasConceptScore W3090791806C28719098 @default.
- W3090791806 hasConceptScore W3090791806C31258907 @default.