Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285179967> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4285179967 endingPage "82406" @default.
- W4285179967 startingPage "82396" @default.
- W4285179967 abstract "The success of convolutional neural networks (CNNs) benefits from the stacking of convolutional layers, which improves the model’s receptive field for image data but also causes a decrease in inference speed. To improve the inference speed of large convolutional network models without sacrificing performance indicators too much, a data-aware adaptive pruning algorithm is proposed. The algorithm consists of two parts, namely, a channel pruning method based on the attention mechanism and a data-aware pruning policy based on reinforcement learning. Experimental results on the CIFAR-100 dataset show that the performance of the proposed pruning algorithm is reduced by only 2.05%, 1.93% and 5.66% after pruning the VGG19, ResNet56 and EfficientNet networks, respectively, but the speedup ratios are 3.63, 3.35, and 1.14, respectively, and the comprehensive pruning performance is the best. In addition, the generalization ability of the reconstruction model is evaluated on the ImageNet dataset and FGVC Aircraft dataset, and the performance of the proposed algorithm is the best, which shows that the proposed algorithm learns data-related information in the pruning process, that is, it is a data-aware algorithm." @default.
- W4285179967 created "2022-07-14" @default.
- W4285179967 creator A5000485535 @default.
- W4285179967 creator A5006954363 @default.
- W4285179967 creator A5048593713 @default.
- W4285179967 creator A5061764261 @default.
- W4285179967 creator A5080356507 @default.
- W4285179967 creator A5085348062 @default.
- W4285179967 date "2022-01-01" @default.
- W4285179967 modified "2023-09-26" @default.
- W4285179967 title "Data-Aware Adaptive Pruning Model Compression Algorithm Based on a Group Attention Mechanism and Reinforcement Learning" @default.
- W4285179967 cites W2117539524 @default.
- W4285179967 cites W2194775991 @default.
- W4285179967 cites W2588463901 @default.
- W4285179967 cites W2750958979 @default.
- W4285179967 cites W2783538964 @default.
- W4285179967 cites W2798603777 @default.
- W4285179967 cites W2899244816 @default.
- W4285179967 cites W2924515500 @default.
- W4285179967 cites W2940297489 @default.
- W4285179967 cites W2946369859 @default.
- W4285179967 cites W2962851801 @default.
- W4285179967 cites W2963363373 @default.
- W4285179967 cites W2964233199 @default.
- W4285179967 cites W2965862774 @default.
- W4285179967 cites W3034513523 @default.
- W4285179967 cites W3044461098 @default.
- W4285179967 cites W3089550499 @default.
- W4285179967 cites W3129584051 @default.
- W4285179967 cites W566555209 @default.
- W4285179967 doi "https://doi.org/10.1109/access.2022.3188119" @default.
- W4285179967 hasPublicationYear "2022" @default.
- W4285179967 type Work @default.
- W4285179967 citedByCount "1" @default.
- W4285179967 countsByYear W42851799672022 @default.
- W4285179967 crossrefType "journal-article" @default.
- W4285179967 hasAuthorship W4285179967A5000485535 @default.
- W4285179967 hasAuthorship W4285179967A5006954363 @default.
- W4285179967 hasAuthorship W4285179967A5048593713 @default.
- W4285179967 hasAuthorship W4285179967A5061764261 @default.
- W4285179967 hasAuthorship W4285179967A5080356507 @default.
- W4285179967 hasAuthorship W4285179967A5085348062 @default.
- W4285179967 hasBestOaLocation W42851799671 @default.
- W4285179967 hasConcept C108010975 @default.
- W4285179967 hasConcept C11413529 @default.
- W4285179967 hasConcept C119857082 @default.
- W4285179967 hasConcept C134306372 @default.
- W4285179967 hasConcept C153180895 @default.
- W4285179967 hasConcept C154945302 @default.
- W4285179967 hasConcept C173608175 @default.
- W4285179967 hasConcept C177148314 @default.
- W4285179967 hasConcept C2776214188 @default.
- W4285179967 hasConcept C33923547 @default.
- W4285179967 hasConcept C41008148 @default.
- W4285179967 hasConcept C6557445 @default.
- W4285179967 hasConcept C68339613 @default.
- W4285179967 hasConcept C81363708 @default.
- W4285179967 hasConcept C86803240 @default.
- W4285179967 hasConcept C97541855 @default.
- W4285179967 hasConceptScore W4285179967C108010975 @default.
- W4285179967 hasConceptScore W4285179967C11413529 @default.
- W4285179967 hasConceptScore W4285179967C119857082 @default.
- W4285179967 hasConceptScore W4285179967C134306372 @default.
- W4285179967 hasConceptScore W4285179967C153180895 @default.
- W4285179967 hasConceptScore W4285179967C154945302 @default.
- W4285179967 hasConceptScore W4285179967C173608175 @default.
- W4285179967 hasConceptScore W4285179967C177148314 @default.
- W4285179967 hasConceptScore W4285179967C2776214188 @default.
- W4285179967 hasConceptScore W4285179967C33923547 @default.
- W4285179967 hasConceptScore W4285179967C41008148 @default.
- W4285179967 hasConceptScore W4285179967C6557445 @default.
- W4285179967 hasConceptScore W4285179967C68339613 @default.
- W4285179967 hasConceptScore W4285179967C81363708 @default.
- W4285179967 hasConceptScore W4285179967C86803240 @default.
- W4285179967 hasConceptScore W4285179967C97541855 @default.
- W4285179967 hasFunder F4320321001 @default.
- W4285179967 hasFunder F4320321133 @default.
- W4285179967 hasLocation W42851799671 @default.
- W4285179967 hasOpenAccess W4285179967 @default.
- W4285179967 hasPrimaryLocation W42851799671 @default.
- W4285179967 hasRelatedWork W2767651786 @default.
- W4285179967 hasRelatedWork W2899244816 @default.
- W4285179967 hasRelatedWork W2912288872 @default.
- W4285179967 hasRelatedWork W3021430260 @default.
- W4285179967 hasRelatedWork W3027997911 @default.
- W4285179967 hasRelatedWork W3207072508 @default.
- W4285179967 hasRelatedWork W4286251925 @default.
- W4285179967 hasRelatedWork W4287776258 @default.
- W4285179967 hasRelatedWork W4312358390 @default.
- W4285179967 hasRelatedWork W4319083788 @default.
- W4285179967 hasVolume "10" @default.
- W4285179967 isParatext "false" @default.
- W4285179967 isRetracted "false" @default.
- W4285179967 workType "article" @default.