FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385804940> ?p ?o ?g. }

• W4385804940 abstract "Although there are many methods based on deep learning that have superior performance on single image super-resolution (SISR), it is difficult to run in real time on devices with limited computing power. Some recent studies have found that simply relying on reducing parameters or reducing the theoretical FLOPs of the model does not speed up the inference time of the network in a practical sense. Actual speed on the device is probably a better measure than FLOPs. In this work, we propose a new single residual network (SRN). On the one hand, we try to introduce and optimize an attention mechanism module to improve the performance of the network with a relatively small speed loss. On the other hand, we find that residuals in residual blocks do not have a positive impact on networks with adjusted ESA. Therefore, the residual of the network residual block is removed, which not only improves the speed of the network, but also improves the performance of the network. Finally, we reduced the number of channels and the number of residual blocks of the classic model EDSR, and removed the last convolution before the long residual. We set this tuned EDSR as the teacher model and our newly proposed SRN as the student model. Under the joint effect of the original loss and the distillation loss, the performance of the network can be improved without losing the inference time. Combining the above strategies, our proposed model runs much faster than similarly performing models. As an example, we built a Fast and Efficient Network (SRN) and its small version SRN-S, which run 30%-37% faster than the state-of-the-art EISR model: a paper champion RLFN. Furthermore, the shallow version of SRN-S achieves the second-shortest inference time as well as the second-smallest number of activations in the NTIRE2023 challenge. Code will be available at https://github.com/wnxbwyc/SRN." @default.
• W4385804940 created "2023-08-15" @default.
• W4385804940 creator A5022757953 @default.
• W4385804940 creator A5076011239 @default.
• W4385804940 date "2023-06-01" @default.
• W4385804940 modified "2023-10-01" @default.
• W4385804940 title "A Single Residual Network with ESA Modules and Distillation" @default.
• W4385804940 cites W1930824406 @default.
• W4385804940 cites W2047920195 @default.
• W4385804940 cites W2110158442 @default.
• W4385804940 cites W2954930822 @default.
• W4385804940 cites W2971595222 @default.
• W4385804940 cites W3011005573 @default.
• W4385804940 cites W3107716502 @default.
• W4385804940 cites W3110378228 @default.
• W4385804940 cites W3133953507 @default.
• W4385804940 cites W3171125843 @default.
• W4385804940 cites W3190446228 @default.
• W4385804940 cites W4224209592 @default.
• W4385804940 cites W4280581786 @default.
• W4385804940 cites W4280626040 @default.
• W4385804940 cites W4312400283 @default.
• W4385804940 cites W4385805159 @default.
• W4385804940 cites W4385815481 @default.
• W4385804940 doi "https://doi.org/10.1109/cvprw59228.2023.00191" @default.
• W4385804940 hasPublicationYear "2023" @default.
• W4385804940 type Work @default.
• W4385804940 citedByCount "1" @default.
• W4385804940 countsByYear W43858049402023 @default.
• W4385804940 crossrefType "proceedings-article" @default.
• W4385804940 hasAuthorship W4385804940A5022757953 @default.
• W4385804940 hasAuthorship W4385804940A5076011239 @default.
• W4385804940 hasConcept C11413529 @default.
• W4385804940 hasConcept C121332964 @default.
• W4385804940 hasConcept C154945302 @default.
• W4385804940 hasConcept C155512373 @default.
• W4385804940 hasConcept C163258240 @default.
• W4385804940 hasConcept C173608175 @default.
• W4385804940 hasConcept C177264268 @default.
• W4385804940 hasConcept C199360897 @default.
• W4385804940 hasConcept C2524010 @default.
• W4385804940 hasConcept C2776214188 @default.
• W4385804940 hasConcept C2777210771 @default.
• W4385804940 hasConcept C33923547 @default.
• W4385804940 hasConcept C3826847 @default.
• W4385804940 hasConcept C41008148 @default.
• W4385804940 hasConcept C45347329 @default.
• W4385804940 hasConcept C50644808 @default.
• W4385804940 hasConcept C62520636 @default.
• W4385804940 hasConceptScore W4385804940C11413529 @default.
• W4385804940 hasConceptScore W4385804940C121332964 @default.
• W4385804940 hasConceptScore W4385804940C154945302 @default.
• W4385804940 hasConceptScore W4385804940C155512373 @default.
• W4385804940 hasConceptScore W4385804940C163258240 @default.
• W4385804940 hasConceptScore W4385804940C173608175 @default.
• W4385804940 hasConceptScore W4385804940C177264268 @default.
• W4385804940 hasConceptScore W4385804940C199360897 @default.
• W4385804940 hasConceptScore W4385804940C2524010 @default.
• W4385804940 hasConceptScore W4385804940C2776214188 @default.
• W4385804940 hasConceptScore W4385804940C2777210771 @default.
• W4385804940 hasConceptScore W4385804940C33923547 @default.
• W4385804940 hasConceptScore W4385804940C3826847 @default.
• W4385804940 hasConceptScore W4385804940C41008148 @default.
• W4385804940 hasConceptScore W4385804940C45347329 @default.
• W4385804940 hasConceptScore W4385804940C50644808 @default.
• W4385804940 hasConceptScore W4385804940C62520636 @default.
• W4385804940 hasLocation W43858049401 @default.
• W4385804940 hasOpenAccess W4385804940 @default.
• W4385804940 hasPrimaryLocation W43858049401 @default.
• W4385804940 hasRelatedWork W2355215981 @default.
• W4385804940 hasRelatedWork W2896911342 @default.
• W4385804940 hasRelatedWork W2903251150 @default.
• W4385804940 hasRelatedWork W2961623865 @default.
• W4385804940 hasRelatedWork W3044388927 @default.
• W4385804940 hasRelatedWork W3108519006 @default.
• W4385804940 hasRelatedWork W3169052126 @default.
• W4385804940 hasRelatedWork W4377236334 @default.
• W4385804940 hasRelatedWork W4378966496 @default.
• W4385804940 hasRelatedWork W4379740998 @default.
• W4385804940 isParatext "false" @default.
• W4385804940 isRetracted "false" @default.
• W4385804940 workType "article" @default.