Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366241503> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4366241503 endingPage "13" @default.
- W4366241503 startingPage "1" @default.
- W4366241503 abstract "Convolutional neural networks (CNNs) have been successfully applied to various fields. However, CNNs’ overparameterization requires more memory and training time, making it unsuitable for some resource-constrained devices. To address this issue, filter pruning as one of the most efficient ways was proposed. In this article, we propose a feature-discrimination-based filter importance criterion, uniform response criterion (URC), as a key component of filter pruning. It converts the maximum activation responses into probabilities and then measures the importance of the filter through the distribution of these probabilities over classes. However, applying URC directly to global threshold pruning may cause some problems. The first problem is that some layers will be completely pruned under global pruning settings. The second problem is that global threshold pruning neglects that filters in different layers have different importance. To address these issues, we propose hierarchical threshold pruning (HTP) with URC. It performs a pruning step limited in a relatively redundant layer rather than comparing the filters’ importance across all layers, which can avoid some important filters being pruned. The effectiveness of our method benefits from three techniques: 1) measuring filter importance by URC; 2) normalizing filter scores; and 3) conducting prune in relatively redundant layers. Extensive experiments on CIFAR-10/100 and ImageNet show that our method achieves the state-of-the-art performance on multiple benchmarks." @default.
- W4366241503 created "2023-04-20" @default.
- W4366241503 creator A5002285033 @default.
- W4366241503 creator A5020631565 @default.
- W4366241503 creator A5024200684 @default.
- W4366241503 creator A5024541442 @default.
- W4366241503 creator A5044055985 @default.
- W4366241503 creator A5052292368 @default.
- W4366241503 creator A5079087211 @default.
- W4366241503 creator A5083869508 @default.
- W4366241503 creator A5084652695 @default.
- W4366241503 date "2023-01-01" @default.
- W4366241503 modified "2023-09-25" @default.
- W4366241503 title "Hierarchical Threshold Pruning Based on Uniform Response Criterion" @default.
- W4366241503 doi "https://doi.org/10.1109/tnnls.2023.3244994" @default.
- W4366241503 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37071515" @default.
- W4366241503 hasPublicationYear "2023" @default.
- W4366241503 type Work @default.
- W4366241503 citedByCount "1" @default.
- W4366241503 countsByYear W43662415032023 @default.
- W4366241503 crossrefType "journal-article" @default.
- W4366241503 hasAuthorship W4366241503A5002285033 @default.
- W4366241503 hasAuthorship W4366241503A5020631565 @default.
- W4366241503 hasAuthorship W4366241503A5024200684 @default.
- W4366241503 hasAuthorship W4366241503A5024541442 @default.
- W4366241503 hasAuthorship W4366241503A5044055985 @default.
- W4366241503 hasAuthorship W4366241503A5052292368 @default.
- W4366241503 hasAuthorship W4366241503A5079087211 @default.
- W4366241503 hasAuthorship W4366241503A5083869508 @default.
- W4366241503 hasAuthorship W4366241503A5084652695 @default.
- W4366241503 hasConcept C106131492 @default.
- W4366241503 hasConcept C108010975 @default.
- W4366241503 hasConcept C11413529 @default.
- W4366241503 hasConcept C138885662 @default.
- W4366241503 hasConcept C153180895 @default.
- W4366241503 hasConcept C154945302 @default.
- W4366241503 hasConcept C26517878 @default.
- W4366241503 hasConcept C2776401178 @default.
- W4366241503 hasConcept C31972630 @default.
- W4366241503 hasConcept C38652104 @default.
- W4366241503 hasConcept C41008148 @default.
- W4366241503 hasConcept C41895202 @default.
- W4366241503 hasConcept C6557445 @default.
- W4366241503 hasConcept C81363708 @default.
- W4366241503 hasConcept C86803240 @default.
- W4366241503 hasConceptScore W4366241503C106131492 @default.
- W4366241503 hasConceptScore W4366241503C108010975 @default.
- W4366241503 hasConceptScore W4366241503C11413529 @default.
- W4366241503 hasConceptScore W4366241503C138885662 @default.
- W4366241503 hasConceptScore W4366241503C153180895 @default.
- W4366241503 hasConceptScore W4366241503C154945302 @default.
- W4366241503 hasConceptScore W4366241503C26517878 @default.
- W4366241503 hasConceptScore W4366241503C2776401178 @default.
- W4366241503 hasConceptScore W4366241503C31972630 @default.
- W4366241503 hasConceptScore W4366241503C38652104 @default.
- W4366241503 hasConceptScore W4366241503C41008148 @default.
- W4366241503 hasConceptScore W4366241503C41895202 @default.
- W4366241503 hasConceptScore W4366241503C6557445 @default.
- W4366241503 hasConceptScore W4366241503C81363708 @default.
- W4366241503 hasConceptScore W4366241503C86803240 @default.
- W4366241503 hasLocation W43662415031 @default.
- W4366241503 hasLocation W43662415032 @default.
- W4366241503 hasOpenAccess W4366241503 @default.
- W4366241503 hasPrimaryLocation W43662415031 @default.
- W4366241503 hasRelatedWork W2295021132 @default.
- W4366241503 hasRelatedWork W2546942002 @default.
- W4366241503 hasRelatedWork W2765989371 @default.
- W4366241503 hasRelatedWork W2767651786 @default.
- W4366241503 hasRelatedWork W2788292821 @default.
- W4366241503 hasRelatedWork W2886673456 @default.
- W4366241503 hasRelatedWork W2912288872 @default.
- W4366241503 hasRelatedWork W3106036237 @default.
- W4366241503 hasRelatedWork W4285337767 @default.
- W4366241503 hasRelatedWork W564581980 @default.
- W4366241503 isParatext "false" @default.
- W4366241503 isRetracted "false" @default.
- W4366241503 workType "article" @default.