Matches in SemOpenAlex for { <https://semopenalex.org/work/W3008043403> ?p ?o ?g. }
- W3008043403 abstract "Convolutional neural networks (CNNs) have shown dramatic improvements in single image super-resolution (SISR) by using large-scale external samples. Despite their remarkable performance based on the external dataset, they cannot exploit internal information within a specific image. Another problem is that they are applicable only to the specific condition of data that they are supervised. For instance, the low-resolution (LR) image should be a bicubic downsampled noise-free image from a high-resolution (HR) one. To address both issues, zero-shot super-resolution (ZSSR) has been proposed for flexible internal learning. However, they require thousands of gradient updates, i.e., long inference time. In this paper, we present Meta-Transfer Learning for Zero-Shot Super-Resolution (MZSR), which leverages ZSSR. Precisely, it is based on finding a generic initial parameter that is suitable for internal learning. Thus, we can exploit both external and internal information, where one single gradient update can yield quite considerable results. (See Figure 1). With our method, the network can quickly adapt to a given image condition. In this respect, our method can be applied to a large spectrum of image conditions within a fast adaptation process." @default.
- W3008043403 created "2020-03-06" @default.
- W3008043403 creator A5044629097 @default.
- W3008043403 creator A5055171648 @default.
- W3008043403 creator A5080770994 @default.
- W3008043403 date "2020-02-27" @default.
- W3008043403 modified "2023-09-27" @default.
- W3008043403 title "Meta-Transfer Learning for Zero-Shot Super-Resolution" @default.
- W3008043403 cites W1522301498 @default.
- W3008043403 cites W1968660339 @default.
- W3008043403 cites W2041625018 @default.
- W3008043403 cites W2047920195 @default.
- W3008043403 cites W2056370875 @default.
- W3008043403 cites W2108598243 @default.
- W3008043403 cites W2121927366 @default.
- W3008043403 cites W2133665775 @default.
- W3008043403 cites W2165317121 @default.
- W3008043403 cites W2167191464 @default.
- W3008043403 cites W2242218935 @default.
- W3008043403 cites W2472819217 @default.
- W3008043403 cites W2474628748 @default.
- W3008043403 cites W2601450892 @default.
- W3008043403 cites W2604763608 @default.
- W3008043403 cites W2613184245 @default.
- W3008043403 cites W2741137940 @default.
- W3008043403 cites W2794363191 @default.
- W3008043403 cites W2795900505 @default.
- W3008043403 cites W2866634454 @default.
- W3008043403 cites W2912268344 @default.
- W3008043403 cites W2947156405 @default.
- W3008043403 cites W2947376905 @default.
- W3008043403 cites W2962723986 @default.
- W3008043403 cites W2962737939 @default.
- W3008043403 cites W2962814024 @default.
- W3008043403 cites W2963303956 @default.
- W3008043403 cites W2963341924 @default.
- W3008043403 cites W2963371846 @default.
- W3008043403 cites W2963372104 @default.
- W3008043403 cites W2963470893 @default.
- W3008043403 cites W2963547174 @default.
- W3008043403 cites W2963580001 @default.
- W3008043403 cites W2963610452 @default.
- W3008043403 cites W2963645458 @default.
- W3008043403 cites W2963729050 @default.
- W3008043403 cites W2963943197 @default.
- W3008043403 cites W2964046397 @default.
- W3008043403 cites W2964105864 @default.
- W3008043403 cites W2964112702 @default.
- W3008043403 cites W2964277374 @default.
- W3008043403 cites W2982041717 @default.
- W3008043403 cites W3009014607 @default.
- W3008043403 cites W3105700508 @default.
- W3008043403 hasPublicationYear "2020" @default.
- W3008043403 type Work @default.
- W3008043403 sameAs 3008043403 @default.
- W3008043403 citedByCount "1" @default.
- W3008043403 countsByYear W30080434032021 @default.
- W3008043403 crossrefType "posted-content" @default.
- W3008043403 hasAuthorship W3008043403A5044629097 @default.
- W3008043403 hasAuthorship W3008043403A5055171648 @default.
- W3008043403 hasAuthorship W3008043403A5080770994 @default.
- W3008043403 hasConcept C111919701 @default.
- W3008043403 hasConcept C11413529 @default.
- W3008043403 hasConcept C115961682 @default.
- W3008043403 hasConcept C119857082 @default.
- W3008043403 hasConcept C138268822 @default.
- W3008043403 hasConcept C150899416 @default.
- W3008043403 hasConcept C153180895 @default.
- W3008043403 hasConcept C154945302 @default.
- W3008043403 hasConcept C165696696 @default.
- W3008043403 hasConcept C171836373 @default.
- W3008043403 hasConcept C2776214188 @default.
- W3008043403 hasConcept C31972630 @default.
- W3008043403 hasConcept C38652104 @default.
- W3008043403 hasConcept C41008148 @default.
- W3008043403 hasConcept C49608258 @default.
- W3008043403 hasConcept C81363708 @default.
- W3008043403 hasConcept C98045186 @default.
- W3008043403 hasConceptScore W3008043403C111919701 @default.
- W3008043403 hasConceptScore W3008043403C11413529 @default.
- W3008043403 hasConceptScore W3008043403C115961682 @default.
- W3008043403 hasConceptScore W3008043403C119857082 @default.
- W3008043403 hasConceptScore W3008043403C138268822 @default.
- W3008043403 hasConceptScore W3008043403C150899416 @default.
- W3008043403 hasConceptScore W3008043403C153180895 @default.
- W3008043403 hasConceptScore W3008043403C154945302 @default.
- W3008043403 hasConceptScore W3008043403C165696696 @default.
- W3008043403 hasConceptScore W3008043403C171836373 @default.
- W3008043403 hasConceptScore W3008043403C2776214188 @default.
- W3008043403 hasConceptScore W3008043403C31972630 @default.
- W3008043403 hasConceptScore W3008043403C38652104 @default.
- W3008043403 hasConceptScore W3008043403C41008148 @default.
- W3008043403 hasConceptScore W3008043403C49608258 @default.
- W3008043403 hasConceptScore W3008043403C81363708 @default.
- W3008043403 hasConceptScore W3008043403C98045186 @default.
- W3008043403 hasLocation W30080434031 @default.
- W3008043403 hasOpenAccess W3008043403 @default.
- W3008043403 hasPrimaryLocation W30080434031 @default.
- W3008043403 hasRelatedWork W1985595620 @default.
- W3008043403 hasRelatedWork W2605134680 @default.