FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385804987> ?p ?o ?g. }

• W4385804987 abstract "Recently, single image super-resolution (SISR) has made great progress, especially through the combination of convolutional neural network (CNN) and Transformer, but the huge model complexity is not desirable for the efficient image super-resolution (EISR), nor is it affordable for edge devices. As a result, many lightweight methods have been investigated for EISR, such as distillation and pruning. However, investigating more powerful attention mechanisms is also a promising solution to improve network efficiency. In this paper, we propose a multi-level dispersion residual network (MDRN) for EISR. As the basic block of MDRN, enhanced attention distillation block (EADB) includes the proposed multi-level dispersion spatial attention (MDSA) and enhanced contrast-aware channel attention (ECCA), respectively. MDSA introduces multi-scale and variance information to obtain more accurate spatial attention distribution. ECCA effectively combines lightweight convolution layers and residual connections to improve the efficiency of channel attention. The experimental results show that the proposed methods are effective and our MDRN achieves a better balance of performance and complexity than the SOTA models. In addition, we won the first place in the model complexity track of the NTIRE 2023 Efficient SR Challenge. The code is available at https://github.com/bbbolt/MDRN." @default.
• W4385804987 created "2023-08-15" @default.
• W4385804987 creator A5016888447 @default.
• W4385804987 creator A5017740044 @default.
• W4385804987 creator A5046092151 @default.
• W4385804987 creator A5054497576 @default.
• W4385804987 creator A5061210370 @default.
• W4385804987 creator A5074575311 @default.
• W4385804987 creator A5077178192 @default.
• W4385804987 creator A5086791779 @default.
• W4385804987 creator A5092315638 @default.
• W4385804987 date "2023-06-01" @default.
• W4385804987 modified "2023-10-01" @default.
• W4385804987 title "Multi-level Dispersion Residual Network for Efficient Image Super-Resolution" @default.
• W4385804987 cites W1791560514 @default.
• W4385804987 cites W1930824406 @default.
• W4385804987 cites W2047920195 @default.
• W4385804987 cites W2121927366 @default.
• W4385804987 cites W2192954843 @default.
• W4385804987 cites W2214802144 @default.
• W4385804987 cites W2476548250 @default.
• W4385804987 cites W2741137940 @default.
• W4385804987 cites W2747898905 @default.
• W4385804987 cites W2752782242 @default.
• W4385804987 cites W2795024892 @default.
• W4385804987 cites W2954930822 @default.
• W4385804987 cites W2963372104 @default.
• W4385804987 cites W2964125708 @default.
• W4385804987 cites W3011005573 @default.
• W4385804987 cites W3015342281 @default.
• W4385804987 cites W3034247386 @default.
• W4385804987 cites W3035421056 @default.
• W4385804987 cites W3085109118 @default.
• W4385804987 cites W3105328221 @default.
• W4385804987 cites W3138516171 @default.
• W4385804987 cites W3167976421 @default.
• W4385804987 cites W3206130237 @default.
• W4385804987 cites W3207918547 @default.
• W4385804987 cites W4224209592 @default.
• W4385804987 cites W4280491778 @default.
• W4385804987 cites W4280581786 @default.
• W4385804987 cites W4280626040 @default.
• W4385804987 cites W4292794827 @default.
• W4385804987 cites W4292829111 @default.
• W4385804987 cites W4385805159 @default.
• W4385804987 cites W4385815481 @default.
• W4385804987 doi "https://doi.org/10.1109/cvprw59228.2023.00167" @default.
• W4385804987 hasPublicationYear "2023" @default.
• W4385804987 type Work @default.
• W4385804987 citedByCount "1" @default.
• W4385804987 countsByYear W43858049872023 @default.
• W4385804987 crossrefType "proceedings-article" @default.
• W4385804987 hasAuthorship W4385804987A5016888447 @default.
• W4385804987 hasAuthorship W4385804987A5017740044 @default.
• W4385804987 hasAuthorship W4385804987A5046092151 @default.
• W4385804987 hasAuthorship W4385804987A5054497576 @default.
• W4385804987 hasAuthorship W4385804987A5061210370 @default.
• W4385804987 hasAuthorship W4385804987A5074575311 @default.
• W4385804987 hasAuthorship W4385804987A5077178192 @default.
• W4385804987 hasAuthorship W4385804987A5086791779 @default.
• W4385804987 hasAuthorship W4385804987A5092315638 @default.
• W4385804987 hasConcept C113775141 @default.
• W4385804987 hasConcept C11413529 @default.
• W4385804987 hasConcept C154945302 @default.
• W4385804987 hasConcept C155512373 @default.
• W4385804987 hasConcept C162307627 @default.
• W4385804987 hasConcept C205372480 @default.
• W4385804987 hasConcept C2524010 @default.
• W4385804987 hasConcept C2777210771 @default.
• W4385804987 hasConcept C33923547 @default.
• W4385804987 hasConcept C41008148 @default.
• W4385804987 hasConcept C45347329 @default.
• W4385804987 hasConcept C50644808 @default.
• W4385804987 hasConcept C81363708 @default.
• W4385804987 hasConceptScore W4385804987C113775141 @default.
• W4385804987 hasConceptScore W4385804987C11413529 @default.
• W4385804987 hasConceptScore W4385804987C154945302 @default.
• W4385804987 hasConceptScore W4385804987C155512373 @default.
• W4385804987 hasConceptScore W4385804987C162307627 @default.
• W4385804987 hasConceptScore W4385804987C205372480 @default.
• W4385804987 hasConceptScore W4385804987C2524010 @default.
• W4385804987 hasConceptScore W4385804987C2777210771 @default.
• W4385804987 hasConceptScore W4385804987C33923547 @default.
• W4385804987 hasConceptScore W4385804987C41008148 @default.
• W4385804987 hasConceptScore W4385804987C45347329 @default.
• W4385804987 hasConceptScore W4385804987C50644808 @default.
• W4385804987 hasConceptScore W4385804987C81363708 @default.
• W4385804987 hasFunder F4320321001 @default.
• W4385804987 hasLocation W43858049871 @default.
• W4385804987 hasOpenAccess W4385804987 @default.
• W4385804987 hasPrimaryLocation W43858049871 @default.
• W4385804987 hasRelatedWork W2610482638 @default.
• W4385804987 hasRelatedWork W2766634277 @default.
• W4385804987 hasRelatedWork W2939136205 @default.
• W4385804987 hasRelatedWork W2961623865 @default.
• W4385804987 hasRelatedWork W2971742398 @default.
• W4385804987 hasRelatedWork W3052481912 @default.
• W4385804987 hasRelatedWork W3127017759 @default.
• W4385804987 hasRelatedWork W3160916081 @default.
• W4385804987 hasRelatedWork W4312417841 @default.

• next