Matches in SemOpenAlex for { <https://semopenalex.org/work/W4293652170> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4293652170 endingPage "166" @default.
- W4293652170 startingPage "157" @default.
- W4293652170 abstract "Recently, the attention mechanism became the key issue for image super-resolution (SR) because it has the ability to extract different features from the image according to the used attention type. Despite the great success of attention-based methods, the conflict among features of different attention types can affect the SR performance. In this paper, we propose an efficient single image SR model called balanced spatial feature distillation and pyramid attention (BSPAN). The idea of BSPAN is based on the trade-off among the extracted features of different attention types. Also, we propose a balanced spatial feature distillation block (BSFDB) as the backbone of BSPAN so that the network can effectively advantage from the different attention features. Two different attention types, namely spatial attention residual feature distillation (SARFD) and classical attention (CA) are considered in the BSFDB to achieve a leveling between them based on the contents of the low-resolution feature map using the balancing attention block. The BSFDB block is designed to improve the SR performance and has lightweight parameters and low computation complexity. Moreover, to further improve the SR performance, the pyramid attention is introduced in the middle of the BSPAN network for extracting long-range features at a variety of locations and scales. Evaluation based on five benchmark datasets, we concluded that the balancing between features of a variety of attention types can effectively improve the SR performance. So, the proposed BSPAN model achieves significant enhancements in comparison with the state-of-the-art and superior visual quality and reconstruction accuracy." @default.
- W4293652170 created "2022-08-31" @default.
- W4293652170 creator A5012461549 @default.
- W4293652170 creator A5018265021 @default.
- W4293652170 creator A5054897331 @default.
- W4293652170 creator A5080452157 @default.
- W4293652170 date "2022-10-01" @default.
- W4293652170 modified "2023-09-29" @default.
- W4293652170 title "Balanced Spatial Feature Distillation and Pyramid Attention Network for Lightweight Image Super-resolution" @default.
- W4293652170 cites W2016482162 @default.
- W4293652170 cites W2133665775 @default.
- W4293652170 cites W2192954843 @default.
- W4293652170 cites W2503339013 @default.
- W4293652170 cites W2593697158 @default.
- W4293652170 cites W2886209123 @default.
- W4293652170 cites W2887695188 @default.
- W4293652170 cites W2918300468 @default.
- W4293652170 cites W2941201280 @default.
- W4293652170 cites W2941646209 @default.
- W4293652170 cites W2963986095 @default.
- W4293652170 cites W2965517251 @default.
- W4293652170 cites W3008237812 @default.
- W4293652170 cites W3013529009 @default.
- W4293652170 cites W3018586778 @default.
- W4293652170 cites W3032400974 @default.
- W4293652170 cites W3035378062 @default.
- W4293652170 cites W3088103684 @default.
- W4293652170 cites W3089400682 @default.
- W4293652170 cites W3093960910 @default.
- W4293652170 cites W3096739052 @default.
- W4293652170 cites W3113560462 @default.
- W4293652170 cites W3167998894 @default.
- W4293652170 cites W4206597275 @default.
- W4293652170 cites W4210678533 @default.
- W4293652170 cites W54257720 @default.
- W4293652170 doi "https://doi.org/10.1016/j.neucom.2022.08.053" @default.
- W4293652170 hasPublicationYear "2022" @default.
- W4293652170 type Work @default.
- W4293652170 citedByCount "7" @default.
- W4293652170 countsByYear W42936521702023 @default.
- W4293652170 crossrefType "journal-article" @default.
- W4293652170 hasAuthorship W4293652170A5012461549 @default.
- W4293652170 hasAuthorship W4293652170A5018265021 @default.
- W4293652170 hasAuthorship W4293652170A5054897331 @default.
- W4293652170 hasAuthorship W4293652170A5080452157 @default.
- W4293652170 hasConcept C115961682 @default.
- W4293652170 hasConcept C138885662 @default.
- W4293652170 hasConcept C141239990 @default.
- W4293652170 hasConcept C142575187 @default.
- W4293652170 hasConcept C153180895 @default.
- W4293652170 hasConcept C154945302 @default.
- W4293652170 hasConcept C205372480 @default.
- W4293652170 hasConcept C2524010 @default.
- W4293652170 hasConcept C2776401178 @default.
- W4293652170 hasConcept C31972630 @default.
- W4293652170 hasConcept C33923547 @default.
- W4293652170 hasConcept C41008148 @default.
- W4293652170 hasConcept C41895202 @default.
- W4293652170 hasConceptScore W4293652170C115961682 @default.
- W4293652170 hasConceptScore W4293652170C138885662 @default.
- W4293652170 hasConceptScore W4293652170C141239990 @default.
- W4293652170 hasConceptScore W4293652170C142575187 @default.
- W4293652170 hasConceptScore W4293652170C153180895 @default.
- W4293652170 hasConceptScore W4293652170C154945302 @default.
- W4293652170 hasConceptScore W4293652170C205372480 @default.
- W4293652170 hasConceptScore W4293652170C2524010 @default.
- W4293652170 hasConceptScore W4293652170C2776401178 @default.
- W4293652170 hasConceptScore W4293652170C31972630 @default.
- W4293652170 hasConceptScore W4293652170C33923547 @default.
- W4293652170 hasConceptScore W4293652170C41008148 @default.
- W4293652170 hasConceptScore W4293652170C41895202 @default.
- W4293652170 hasFunder F4320321001 @default.
- W4293652170 hasFunder F4320335777 @default.
- W4293652170 hasLocation W42936521701 @default.
- W4293652170 hasOpenAccess W4293652170 @default.
- W4293652170 hasPrimaryLocation W42936521701 @default.
- W4293652170 hasRelatedWork W1504288058 @default.
- W4293652170 hasRelatedWork W2017205855 @default.
- W4293652170 hasRelatedWork W2031347084 @default.
- W4293652170 hasRelatedWork W2048505601 @default.
- W4293652170 hasRelatedWork W2167293474 @default.
- W4293652170 hasRelatedWork W2331674254 @default.
- W4293652170 hasRelatedWork W2358403311 @default.
- W4293652170 hasRelatedWork W2577364290 @default.
- W4293652170 hasRelatedWork W2979079341 @default.
- W4293652170 hasRelatedWork W3042897387 @default.
- W4293652170 hasVolume "509" @default.
- W4293652170 isParatext "false" @default.
- W4293652170 isRetracted "false" @default.
- W4293652170 workType "article" @default.