FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2953231776> ?p ?o ?g. }

• W2953231776 abstract "Large deep networks have demonstrated competitive performance in single image super-resolution (SISR), with a huge volume of data involved. However, in real-world scenarios, due to the limited accessible training pairs, large models exhibit undesirable behaviors such as overfitting and memorization. To suppress model overfitting and further enjoy the merits of large model capacity, we thoroughly investigate generic approaches for supplying additional training data pairs. In particular, we introduce a simple learning principle MixUp to train networks on interpolations of sample pairs, which encourages networks to support linear behavior in-between training samples. In addition, we propose a data synthesis method with learned degradation, enabling models to use extra high-quality images with higher content diversity. This strategy proves to be successful in reducing biases of data. By combining these components -- MixUp and synthetic training data, large models can be trained without overfitting under very limited data samples and achieve satisfactory generalization performance. Our method won the second place in NTIRE2019 Real SR Challenge." @default.
• W2953231776 created "2019-06-27" @default.
• W2953231776 creator A5023845728 @default.
• W2953231776 creator A5053225991 @default.
• W2953231776 creator A5072861783 @default.
• W2953231776 creator A5078100073 @default.
• W2953231776 date "2019-06-11" @default.
• W2953231776 modified "2023-09-27" @default.
• W2953231776 title "Suppressing Model Overfitting for Image Super-Resolution Networks" @default.
• W2953231776 cites W1600737329 @default.
• W2953231776 cites W1677182931 @default.
• W2953231776 cites W1885185971 @default.
• W2953231776 cites W1901129140 @default.
• W2953231776 cites W2133665775 @default.
• W2953231776 cites W2214802144 @default.
• W2953231776 cites W2242218935 @default.
• W2953231776 cites W2469582947 @default.
• W2953231776 cites W2503339013 @default.
• W2953231776 cites W2739757502 @default.
• W2953231776 cites W2741137940 @default.
• W2953231776 cites W2746314669 @default.
• W2953231776 cites W2767019926 @default.
• W2953231776 cites W2770173563 @default.
• W2953231776 cites W2775795276 @default.
• W2953231776 cites W2783482415 @default.
• W2953231776 cites W2804047946 @default.
• W2953231776 cites W2866634454 @default.
• W2953231776 cites W2883102461 @default.
• W2953231776 cites W2891158090 @default.
• W2953231776 cites W2899771611 @default.
• W2953231776 cites W2902617128 @default.
• W2953231776 cites W2932253358 @default.
• W2953231776 cites W2943960148 @default.
• W2953231776 cites W2944221070 @default.
• W2953231776 cites W2962814024 @default.
• W2953231776 cites W2963070594 @default.
• W2953231776 cites W2963216553 @default.
• W2953231776 cites W2963352069 @default.
• W2953231776 cites W2963372104 @default.
• W2953231776 cites W2963399829 @default.
• W2953231776 cites W2963645458 @default.
• W2953231776 cites W2963704386 @default.
• W2953231776 cites W2963708445 @default.
• W2953231776 cites W2963725279 @default.
• W2953231776 cites W2964101377 @default.
• W2953231776 cites W2964121744 @default.
• W2953231776 cites W2964125708 @default.
• W2953231776 cites W2987150909 @default.
• W2953231776 cites W2998508940 @default.
• W2953231776 cites W54257720 @default.
• W2953231776 cites W2963543962 @default.
• W2953231776 hasPublicationYear "2019" @default.
• W2953231776 type Work @default.
• W2953231776 sameAs 2953231776 @default.
• W2953231776 citedByCount "0" @default.
• W2953231776 crossrefType "posted-content" @default.
• W2953231776 hasAuthorship W2953231776A5023845728 @default.
• W2953231776 hasAuthorship W2953231776A5053225991 @default.
• W2953231776 hasAuthorship W2953231776A5072861783 @default.
• W2953231776 hasAuthorship W2953231776A5078100073 @default.
• W2953231776 hasConcept C111472728 @default.
• W2953231776 hasConcept C115961682 @default.
• W2953231776 hasConcept C119857082 @default.
• W2953231776 hasConcept C124101348 @default.
• W2953231776 hasConcept C134306372 @default.
• W2953231776 hasConcept C138885662 @default.
• W2953231776 hasConcept C153180895 @default.
• W2953231776 hasConcept C154945302 @default.
• W2953231776 hasConcept C177148314 @default.
• W2953231776 hasConcept C185592680 @default.
• W2953231776 hasConcept C198531522 @default.
• W2953231776 hasConcept C22019652 @default.
• W2953231776 hasConcept C2780586882 @default.
• W2953231776 hasConcept C33923547 @default.
• W2953231776 hasConcept C41008148 @default.
• W2953231776 hasConcept C43617362 @default.
• W2953231776 hasConcept C50644808 @default.
• W2953231776 hasConcept C51632099 @default.
• W2953231776 hasConceptScore W2953231776C111472728 @default.
• W2953231776 hasConceptScore W2953231776C115961682 @default.
• W2953231776 hasConceptScore W2953231776C119857082 @default.
• W2953231776 hasConceptScore W2953231776C124101348 @default.
• W2953231776 hasConceptScore W2953231776C134306372 @default.
• W2953231776 hasConceptScore W2953231776C138885662 @default.
• W2953231776 hasConceptScore W2953231776C153180895 @default.
• W2953231776 hasConceptScore W2953231776C154945302 @default.
• W2953231776 hasConceptScore W2953231776C177148314 @default.
• W2953231776 hasConceptScore W2953231776C185592680 @default.
• W2953231776 hasConceptScore W2953231776C198531522 @default.
• W2953231776 hasConceptScore W2953231776C22019652 @default.
• W2953231776 hasConceptScore W2953231776C2780586882 @default.
• W2953231776 hasConceptScore W2953231776C33923547 @default.
• W2953231776 hasConceptScore W2953231776C41008148 @default.
• W2953231776 hasConceptScore W2953231776C43617362 @default.
• W2953231776 hasConceptScore W2953231776C50644808 @default.
• W2953231776 hasConceptScore W2953231776C51632099 @default.
• W2953231776 hasOpenAccess W2953231776 @default.
• W2953231776 hasRelatedWork W2172029476 @default.
• W2953231776 hasRelatedWork W2593807705 @default.
• W2953231776 hasRelatedWork W2787751390 @default.

• next