FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4280491778> ?p ?o ?g. }

• W4280491778 abstract "Deep learning based approaches has achieved great performance in single image super-resolution (SISR). However, recent advances in efficient super-resolution focus on reducing the number of parameters and FLOPs, and they aggregate more powerful features by improving feature utilization through complex layer connection strategies. These structures may not be necessary to achieve higher running speed, which makes them difficult to be deployed to resource-constrained devices. In this work, we propose a novel Residual Local Feature Network (RLFN). The main idea is using three convolutional layers for residual local feature learning to simplify feature aggregation, which achieves a good trade-off between model performance and inference time. Moreover, we revisit the popular contrastive loss and observe that the selection of intermediate features of its feature extractor has great influence on the performance. Besides, we propose a novel multi-stage warm-start training strategy. In each stage, the pre-trained weights from previous stages are utilized to improve the model performance. Combined with the improved contrastive loss and training strategy, the proposed RLFN outperforms all the state-of-the-art efficient image SR models in terms of runtime while maintaining both PSNR and SSIM for SR. In addition, we won the first place in the runtime track of the NTIRE 2022 efficient super-resolution challenge. Code will be available at https://github.com/fyan111/RLFN." @default.
• W4280491778 created "2022-05-22" @default.
• W4280491778 creator A5010771903 @default.
• W4280491778 creator A5041983865 @default.
• W4280491778 creator A5043750095 @default.
• W4280491778 creator A5073867140 @default.
• W4280491778 creator A5078392945 @default.
• W4280491778 creator A5080087400 @default.
• W4280491778 creator A5081997237 @default.
• W4280491778 creator A5086939495 @default.
• W4280491778 date "2022-06-01" @default.
• W4280491778 modified "2023-10-16" @default.
• W4280491778 title "Residual Local Feature Network for Efficient Super-Resolution" @default.
• W4280491778 cites W1930824406 @default.
• W4280491778 cites W2121927366 @default.
• W4280491778 cites W2214802144 @default.
• W4280491778 cites W2242218935 @default.
• W4280491778 cites W2476548250 @default.
• W4280491778 cites W2607041014 @default.
• W4280491778 cites W2741137940 @default.
• W4280491778 cites W2747898905 @default.
• W4280491778 cites W2808168148 @default.
• W4280491778 cites W2963372104 @default.
• W4280491778 cites W2963676087 @default.
• W4280491778 cites W3034247386 @default.
• W4280491778 cites W3035068513 @default.
• W4280491778 cites W3035524453 @default.
• W4280491778 cites W3105328221 @default.
• W4280491778 cites W3114632476 @default.
• W4280491778 cites W3167976421 @default.
• W4280491778 cites W3170204166 @default.
• W4280491778 cites W3171125843 @default.
• W4280491778 cites W3173269149 @default.
• W4280491778 cites W3173515979 @default.
• W4280491778 cites W3174531399 @default.
• W4280491778 cites W3175558068 @default.
• W4280491778 cites W3176935213 @default.
• W4280491778 cites W3190446228 @default.
• W4280491778 cites W3202277597 @default.
• W4280491778 cites W3206130237 @default.
• W4280491778 cites W3207918547 @default.
• W4280491778 cites W4280626040 @default.
• W4280491778 doi "https://doi.org/10.1109/cvprw56347.2022.00092" @default.
• W4280491778 hasPublicationYear "2022" @default.
• W4280491778 type Work @default.
• W4280491778 citedByCount "39" @default.
• W4280491778 countsByYear W42804917782022 @default.
• W4280491778 countsByYear W42804917782023 @default.
• W4280491778 crossrefType "proceedings-article" @default.
• W4280491778 hasAuthorship W4280491778A5010771903 @default.
• W4280491778 hasAuthorship W4280491778A5041983865 @default.
• W4280491778 hasAuthorship W4280491778A5043750095 @default.
• W4280491778 hasAuthorship W4280491778A5073867140 @default.
• W4280491778 hasAuthorship W4280491778A5078392945 @default.
• W4280491778 hasAuthorship W4280491778A5080087400 @default.
• W4280491778 hasAuthorship W4280491778A5081997237 @default.
• W4280491778 hasAuthorship W4280491778A5086939495 @default.
• W4280491778 hasBestOaLocation W42804917782 @default.
• W4280491778 hasConcept C108583219 @default.
• W4280491778 hasConcept C11413529 @default.
• W4280491778 hasConcept C120665830 @default.
• W4280491778 hasConcept C121332964 @default.
• W4280491778 hasConcept C138885662 @default.
• W4280491778 hasConcept C153180895 @default.
• W4280491778 hasConcept C154945302 @default.
• W4280491778 hasConcept C155512373 @default.
• W4280491778 hasConcept C173608175 @default.
• W4280491778 hasConcept C177264268 @default.
• W4280491778 hasConcept C178790620 @default.
• W4280491778 hasConcept C185592680 @default.
• W4280491778 hasConcept C192209626 @default.
• W4280491778 hasConcept C199360897 @default.
• W4280491778 hasConcept C2776214188 @default.
• W4280491778 hasConcept C2776401178 @default.
• W4280491778 hasConcept C2776760102 @default.
• W4280491778 hasConcept C2779227376 @default.
• W4280491778 hasConcept C3826847 @default.
• W4280491778 hasConcept C41008148 @default.
• W4280491778 hasConcept C41895202 @default.
• W4280491778 hasConcept C52622490 @default.
• W4280491778 hasConcept C81363708 @default.
• W4280491778 hasConceptScore W4280491778C108583219 @default.
• W4280491778 hasConceptScore W4280491778C11413529 @default.
• W4280491778 hasConceptScore W4280491778C120665830 @default.
• W4280491778 hasConceptScore W4280491778C121332964 @default.
• W4280491778 hasConceptScore W4280491778C138885662 @default.
• W4280491778 hasConceptScore W4280491778C153180895 @default.
• W4280491778 hasConceptScore W4280491778C154945302 @default.
• W4280491778 hasConceptScore W4280491778C155512373 @default.
• W4280491778 hasConceptScore W4280491778C173608175 @default.
• W4280491778 hasConceptScore W4280491778C177264268 @default.
• W4280491778 hasConceptScore W4280491778C178790620 @default.
• W4280491778 hasConceptScore W4280491778C185592680 @default.
• W4280491778 hasConceptScore W4280491778C192209626 @default.
• W4280491778 hasConceptScore W4280491778C199360897 @default.
• W4280491778 hasConceptScore W4280491778C2776214188 @default.
• W4280491778 hasConceptScore W4280491778C2776401178 @default.
• W4280491778 hasConceptScore W4280491778C2776760102 @default.
• W4280491778 hasConceptScore W4280491778C2779227376 @default.
• W4280491778 hasConceptScore W4280491778C3826847 @default.

• next