Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385804939> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W4385804939 abstract "Efficient deep learning-based approaches have achieved remarkable performance in single image super-resolution. However, recent studies on efficient super-resolution have mainly focused on reducing the number of parameters and floating-point operations through various network designs. Although these methods can decrease the number of parameters and floating-point operations, they may not necessarily reduce actual running time. To address this issue, we propose a novel multi-stage lightweight network boosting method, which can enable lightweight networks to achieve outstanding performance. Specifically, we leverage enhanced high-resolution output as additional supervision to improve the learning ability of lightweight student networks. Upon convergence of the student network, we further simplify our network structure to a more lightweight level using reparameterization techniques and iterative network pruning. Meanwhile, we adopt an effective lightweight network training strategy that combines multi-anchor distillation and progressive learning, enabling the lightweight network to achieve outstanding performance. Ultimately, our proposed method achieves the fastest inference time among all participants in the NTIRE 2023 efficient super-resolution challenge while maintaining competitive super-resolution performance. Additionally, extensive experiments are conducted to demonstrate the effectiveness of the proposed components. The results show that our approach achieves comparable performance in representative dataset DIV2K, both qualitatively and quantitatively, with faster inference and fewer number of network parameters." @default.
- W4385804939 created "2023-08-15" @default.
- W4385804939 creator A5027295717 @default.
- W4385804939 creator A5035064408 @default.
- W4385804939 creator A5039387461 @default.
- W4385804939 creator A5064666806 @default.
- W4385804939 creator A5074564038 @default.
- W4385804939 creator A5078395312 @default.
- W4385804939 creator A5090606731 @default.
- W4385804939 date "2023-06-01" @default.
- W4385804939 modified "2023-10-16" @default.
- W4385804939 title "DIPNet: Efficiency Distillation and Iterative Pruning for Image Super-Resolution" @default.
- W4385804939 cites W2214802144 @default.
- W4385804939 cites W2242218935 @default.
- W4385804939 cites W2476548250 @default.
- W4385804939 cites W2607041014 @default.
- W4385804939 cites W2741137940 @default.
- W4385804939 cites W2747898905 @default.
- W4385804939 cites W2795024892 @default.
- W4385804939 cites W2948475055 @default.
- W4385804939 cites W2962814024 @default.
- W4385804939 cites W2963037581 @default.
- W4385804939 cites W2963372104 @default.
- W4385804939 cites W2963676087 @default.
- W4385804939 cites W2963729050 @default.
- W4385804939 cites W2964101377 @default.
- W4385804939 cites W3000775737 @default.
- W4385804939 cites W3034785019 @default.
- W4385804939 cites W3105328221 @default.
- W4385804939 cites W3167976421 @default.
- W4385804939 cites W3173515979 @default.
- W4385804939 cites W3174816433 @default.
- W4385804939 cites W3206130237 @default.
- W4385804939 cites W3207918547 @default.
- W4385804939 cites W4224209592 @default.
- W4385804939 cites W4224230993 @default.
- W4385804939 cites W4224299924 @default.
- W4385804939 cites W4280491778 @default.
- W4385804939 cites W4280626040 @default.
- W4385804939 cites W4312509301 @default.
- W4385804939 cites W4312727918 @default.
- W4385804939 cites W4385805159 @default.
- W4385804939 cites W4385815481 @default.
- W4385804939 doi "https://doi.org/10.1109/cvprw59228.2023.00170" @default.
- W4385804939 hasPublicationYear "2023" @default.
- W4385804939 type Work @default.
- W4385804939 citedByCount "1" @default.
- W4385804939 countsByYear W43858049392023 @default.
- W4385804939 crossrefType "proceedings-article" @default.
- W4385804939 hasAuthorship W4385804939A5027295717 @default.
- W4385804939 hasAuthorship W4385804939A5035064408 @default.
- W4385804939 hasAuthorship W4385804939A5039387461 @default.
- W4385804939 hasAuthorship W4385804939A5064666806 @default.
- W4385804939 hasAuthorship W4385804939A5074564038 @default.
- W4385804939 hasAuthorship W4385804939A5078395312 @default.
- W4385804939 hasAuthorship W4385804939A5090606731 @default.
- W4385804939 hasBestOaLocation W43858049392 @default.
- W4385804939 hasConcept C108010975 @default.
- W4385804939 hasConcept C113775141 @default.
- W4385804939 hasConcept C11413529 @default.
- W4385804939 hasConcept C119857082 @default.
- W4385804939 hasConcept C153083717 @default.
- W4385804939 hasConcept C154945302 @default.
- W4385804939 hasConcept C203274722 @default.
- W4385804939 hasConcept C2776214188 @default.
- W4385804939 hasConcept C31258907 @default.
- W4385804939 hasConcept C41008148 @default.
- W4385804939 hasConcept C46686674 @default.
- W4385804939 hasConcept C6557445 @default.
- W4385804939 hasConcept C86803240 @default.
- W4385804939 hasConceptScore W4385804939C108010975 @default.
- W4385804939 hasConceptScore W4385804939C113775141 @default.
- W4385804939 hasConceptScore W4385804939C11413529 @default.
- W4385804939 hasConceptScore W4385804939C119857082 @default.
- W4385804939 hasConceptScore W4385804939C153083717 @default.
- W4385804939 hasConceptScore W4385804939C154945302 @default.
- W4385804939 hasConceptScore W4385804939C203274722 @default.
- W4385804939 hasConceptScore W4385804939C2776214188 @default.
- W4385804939 hasConceptScore W4385804939C31258907 @default.
- W4385804939 hasConceptScore W4385804939C41008148 @default.
- W4385804939 hasConceptScore W4385804939C46686674 @default.
- W4385804939 hasConceptScore W4385804939C6557445 @default.
- W4385804939 hasConceptScore W4385804939C86803240 @default.
- W4385804939 hasLocation W43858049391 @default.
- W4385804939 hasLocation W43858049392 @default.
- W4385804939 hasOpenAccess W4385804939 @default.
- W4385804939 hasPrimaryLocation W43858049391 @default.
- W4385804939 hasRelatedWork W1987859285 @default.
- W4385804939 hasRelatedWork W1996541855 @default.
- W4385804939 hasRelatedWork W2298182397 @default.
- W4385804939 hasRelatedWork W2961085424 @default.
- W4385804939 hasRelatedWork W3037896803 @default.
- W4385804939 hasRelatedWork W3098411449 @default.
- W4385804939 hasRelatedWork W3195168932 @default.
- W4385804939 hasRelatedWork W4225307033 @default.
- W4385804939 hasRelatedWork W4313488044 @default.
- W4385804939 hasRelatedWork W4376274634 @default.
- W4385804939 isParatext "false" @default.
- W4385804939 isRetracted "false" @default.
- W4385804939 workType "article" @default.