Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376852246> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4376852246 abstract "The deeper and wider architectures of recent convolutional neural networks (CNN) are responsible for superior performance in computer vision tasks. However, they also come with an enormous model size and heavy computational cost. Filter pruning (FP) is one of the methods applied to CNNs for compression and acceleration. Various techniques have been recently proposed for filter pruning. We address the limitation of the existing state-of-the-art method and motivate our setup. We develop a novel method for filter selection using sparse approximation of filter weights. We propose an orthogonal matching pursuit (OMP) based algorithm for filter pruning (called FP-OMP). We also propose FP-OMP Search, which address the problem of removal of uniform number of filters from all the layers of a network. FP-OMP Search performs a search over all the layers with a given batch size of filter removal. We evaluate both FP-OMP and FP-OMP Search on benchmark datasets using standard ResNet architectures. Experimental results indicate that FP-OMP Search consistently outperforms the baseline method (LRF) by nearly . We demonstrate both empirically and visually, that FP-OMP Search prunes different number of filters from different layers. Further, timing profile experiments show that FP-OMP improves over the running time of LRF." @default.
- W4376852246 created "2023-05-18" @default.
- W4376852246 creator A5009272947 @default.
- W4376852246 creator A5046910575 @default.
- W4376852246 creator A5078606500 @default.
- W4376852246 creator A5091958537 @default.
- W4376852246 date "2022-10-12" @default.
- W4376852246 modified "2023-09-30" @default.
- W4376852246 title "Accurate and Efficient Channel pruning via Orthogonal Matching Pursuit" @default.
- W4376852246 cites W2127271355 @default.
- W4376852246 cites W2194775991 @default.
- W4376852246 cites W2549139847 @default.
- W4376852246 cites W2736536388 @default.
- W4376852246 cites W2962851801 @default.
- W4376852246 cites W2963363373 @default.
- W4376852246 cites W2963446712 @default.
- W4376852246 cites W2964233199 @default.
- W4376852246 cites W2984618279 @default.
- W4376852246 cites W3034513523 @default.
- W4376852246 cites W3035467254 @default.
- W4376852246 doi "https://doi.org/10.1145/3564121.3564139" @default.
- W4376852246 hasPublicationYear "2022" @default.
- W4376852246 type Work @default.
- W4376852246 citedByCount "0" @default.
- W4376852246 crossrefType "proceedings-article" @default.
- W4376852246 hasAuthorship W4376852246A5009272947 @default.
- W4376852246 hasAuthorship W4376852246A5046910575 @default.
- W4376852246 hasAuthorship W4376852246A5078606500 @default.
- W4376852246 hasAuthorship W4376852246A5091958537 @default.
- W4376852246 hasConcept C106131492 @default.
- W4376852246 hasConcept C108010975 @default.
- W4376852246 hasConcept C11413529 @default.
- W4376852246 hasConcept C124851039 @default.
- W4376852246 hasConcept C13280743 @default.
- W4376852246 hasConcept C153180895 @default.
- W4376852246 hasConcept C154945302 @default.
- W4376852246 hasConcept C156872377 @default.
- W4376852246 hasConcept C185798385 @default.
- W4376852246 hasConcept C205649164 @default.
- W4376852246 hasConcept C31972630 @default.
- W4376852246 hasConcept C41008148 @default.
- W4376852246 hasConcept C6557445 @default.
- W4376852246 hasConcept C81363708 @default.
- W4376852246 hasConcept C86803240 @default.
- W4376852246 hasConceptScore W4376852246C106131492 @default.
- W4376852246 hasConceptScore W4376852246C108010975 @default.
- W4376852246 hasConceptScore W4376852246C11413529 @default.
- W4376852246 hasConceptScore W4376852246C124851039 @default.
- W4376852246 hasConceptScore W4376852246C13280743 @default.
- W4376852246 hasConceptScore W4376852246C153180895 @default.
- W4376852246 hasConceptScore W4376852246C154945302 @default.
- W4376852246 hasConceptScore W4376852246C156872377 @default.
- W4376852246 hasConceptScore W4376852246C185798385 @default.
- W4376852246 hasConceptScore W4376852246C205649164 @default.
- W4376852246 hasConceptScore W4376852246C31972630 @default.
- W4376852246 hasConceptScore W4376852246C41008148 @default.
- W4376852246 hasConceptScore W4376852246C6557445 @default.
- W4376852246 hasConceptScore W4376852246C81363708 @default.
- W4376852246 hasConceptScore W4376852246C86803240 @default.
- W4376852246 hasLocation W43768522461 @default.
- W4376852246 hasOpenAccess W4376852246 @default.
- W4376852246 hasPrimaryLocation W43768522461 @default.
- W4376852246 hasRelatedWork W1895390915 @default.
- W4376852246 hasRelatedWork W2175746458 @default.
- W4376852246 hasRelatedWork W2732542196 @default.
- W4376852246 hasRelatedWork W2738221750 @default.
- W4376852246 hasRelatedWork W2760085659 @default.
- W4376852246 hasRelatedWork W2883200793 @default.
- W4376852246 hasRelatedWork W2949389737 @default.
- W4376852246 hasRelatedWork W2963556241 @default.
- W4376852246 hasRelatedWork W3012978760 @default.
- W4376852246 hasRelatedWork W3093612317 @default.
- W4376852246 isParatext "false" @default.
- W4376852246 isRetracted "false" @default.
- W4376852246 workType "article" @default.