Matches in SemOpenAlex for { <https://semopenalex.org/work/W4213068294> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4213068294 abstract "Since the resurgence of deep neural networks (DNNs), image super-resolution (SR) has recently seen a huge progress in improving the quality of low resolution images, however at the great cost of computations and resources. Recently, there has been several efforts to make DNNs more efficient via quantization. However, SR demands pixel-level accuracy in the system, it is more difficult to perform quantization without significantly sacrificing SR performance. To this end, we introduce a new ultra-low precision yet effective quantization approach specifically designed for SR. In particular, we observe that in recent SR networks, each channel has different distribution characteristics. Thus we propose a channel-wise distribution-aware quantization scheme. Experimental results demonstrate that our proposed quantization, dubbed Distribution-Aware Quantization (DAQ), manages to greatly reduce the computational and resource costs without the significant sacrifice in SR performance, compared to other quantization methods." @default.
- W4213068294 created "2022-02-24" @default.
- W4213068294 creator A5003484891 @default.
- W4213068294 creator A5003678844 @default.
- W4213068294 creator A5046504049 @default.
- W4213068294 creator A5047136540 @default.
- W4213068294 creator A5048206537 @default.
- W4213068294 date "2022-01-01" @default.
- W4213068294 modified "2023-10-09" @default.
- W4213068294 title "DAQ: Channel-Wise Distribution-Aware Quantization for Deep Image Super-Resolution Networks" @default.
- W4213068294 cites W1999085092 @default.
- W4213068294 cites W2003921122 @default.
- W4213068294 cites W2016482162 @default.
- W4213068294 cites W2194775991 @default.
- W4213068294 cites W2242218935 @default.
- W4213068294 cites W2476548250 @default.
- W4213068294 cites W2586654419 @default.
- W4213068294 cites W2741137940 @default.
- W4213068294 cites W2884150179 @default.
- W4213068294 cites W2954048742 @default.
- W4213068294 cites W2963372104 @default.
- W4213068294 cites W2963470893 @default.
- W4213068294 cites W2963480671 @default.
- W4213068294 cites W2964101377 @default.
- W4213068294 cites W2971595222 @default.
- W4213068294 cites W2981751377 @default.
- W4213068294 cites W2998218113 @default.
- W4213068294 cites W3034887213 @default.
- W4213068294 cites W3034940165 @default.
- W4213068294 cites W3096641820 @default.
- W4213068294 cites W3105328221 @default.
- W4213068294 cites W3110378228 @default.
- W4213068294 cites W3176265374 @default.
- W4213068294 cites W3177491619 @default.
- W4213068294 cites W3204989974 @default.
- W4213068294 doi "https://doi.org/10.1109/wacv51458.2022.00099" @default.
- W4213068294 hasPublicationYear "2022" @default.
- W4213068294 type Work @default.
- W4213068294 citedByCount "8" @default.
- W4213068294 countsByYear W42130682942022 @default.
- W4213068294 countsByYear W42130682942023 @default.
- W4213068294 crossrefType "proceedings-article" @default.
- W4213068294 hasAuthorship W4213068294A5003484891 @default.
- W4213068294 hasAuthorship W4213068294A5003678844 @default.
- W4213068294 hasAuthorship W4213068294A5046504049 @default.
- W4213068294 hasAuthorship W4213068294A5047136540 @default.
- W4213068294 hasAuthorship W4213068294A5048206537 @default.
- W4213068294 hasBestOaLocation W42130682942 @default.
- W4213068294 hasConcept C108583219 @default.
- W4213068294 hasConcept C113775141 @default.
- W4213068294 hasConcept C11413529 @default.
- W4213068294 hasConcept C127313418 @default.
- W4213068294 hasConcept C154945302 @default.
- W4213068294 hasConcept C160633673 @default.
- W4213068294 hasConcept C28855332 @default.
- W4213068294 hasConcept C2984842247 @default.
- W4213068294 hasConcept C3019883945 @default.
- W4213068294 hasConcept C3020199158 @default.
- W4213068294 hasConcept C41008148 @default.
- W4213068294 hasConcept C45374587 @default.
- W4213068294 hasConcept C50644808 @default.
- W4213068294 hasConcept C62649853 @default.
- W4213068294 hasConceptScore W4213068294C108583219 @default.
- W4213068294 hasConceptScore W4213068294C113775141 @default.
- W4213068294 hasConceptScore W4213068294C11413529 @default.
- W4213068294 hasConceptScore W4213068294C127313418 @default.
- W4213068294 hasConceptScore W4213068294C154945302 @default.
- W4213068294 hasConceptScore W4213068294C160633673 @default.
- W4213068294 hasConceptScore W4213068294C28855332 @default.
- W4213068294 hasConceptScore W4213068294C2984842247 @default.
- W4213068294 hasConceptScore W4213068294C3019883945 @default.
- W4213068294 hasConceptScore W4213068294C3020199158 @default.
- W4213068294 hasConceptScore W4213068294C41008148 @default.
- W4213068294 hasConceptScore W4213068294C45374587 @default.
- W4213068294 hasConceptScore W4213068294C50644808 @default.
- W4213068294 hasConceptScore W4213068294C62649853 @default.
- W4213068294 hasLocation W42130682941 @default.
- W4213068294 hasLocation W42130682942 @default.
- W4213068294 hasOpenAccess W4213068294 @default.
- W4213068294 hasPrimaryLocation W42130682941 @default.
- W4213068294 hasRelatedWork W2279398222 @default.
- W4213068294 hasRelatedWork W2791691546 @default.
- W4213068294 hasRelatedWork W2915754718 @default.
- W4213068294 hasRelatedWork W2941846814 @default.
- W4213068294 hasRelatedWork W3082895349 @default.
- W4213068294 hasRelatedWork W3091882364 @default.
- W4213068294 hasRelatedWork W3176779650 @default.
- W4213068294 hasRelatedWork W3193983877 @default.
- W4213068294 hasRelatedWork W4299822940 @default.
- W4213068294 hasRelatedWork W4312831135 @default.
- W4213068294 isParatext "false" @default.
- W4213068294 isRetracted "false" @default.
- W4213068294 workType "article" @default.