Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890788829> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2890788829 abstract "Pruning filters is an effective method for accelerating deep neural networks (DNNs), but most existing approaches prune filters on a pre-trained network directly which limits in acceleration. Although each filter has its own effect in DNNs, but if two filters are same with each other, we could prune one safely. In this paper, we add an extra cluster loss term in the loss function which can force filters in each cluster to be similar online. After training, we keep one filter in each cluster and prune others and fine-tune the pruned network to compensate the loss. Particularly, the clusters in every layer can be defined firstly which is effective for pruning DNNs within residual blocks. Extensive experiments on CIFAR10 and CIFR100 benchmarks demonstrate the competitive performance of our proposed filter pruning method." @default.
- W2890788829 created "2018-09-27" @default.
- W2890788829 creator A5010204267 @default.
- W2890788829 creator A5046805800 @default.
- W2890788829 creator A5051332325 @default.
- W2890788829 creator A5078141810 @default.
- W2890788829 date "2018-10-01" @default.
- W2890788829 modified "2023-10-17" @default.
- W2890788829 title "Online Filter Clustering and Pruning for Efficient Convnets" @default.
- W2890788829 cites W2507506703 @default.
- W2890788829 cites W2561516185 @default.
- W2890788829 cites W2604998962 @default.
- W2890788829 cites W2962694340 @default.
- W2890788829 cites W2963363373 @default.
- W2890788829 cites W2964233199 @default.
- W2890788829 doi "https://doi.org/10.1109/icip.2018.8451123" @default.
- W2890788829 hasPublicationYear "2018" @default.
- W2890788829 type Work @default.
- W2890788829 sameAs 2890788829 @default.
- W2890788829 citedByCount "12" @default.
- W2890788829 countsByYear W28907888292019 @default.
- W2890788829 countsByYear W28907888292020 @default.
- W2890788829 countsByYear W28907888292021 @default.
- W2890788829 countsByYear W28907888292022 @default.
- W2890788829 countsByYear W28907888292023 @default.
- W2890788829 crossrefType "proceedings-article" @default.
- W2890788829 hasAuthorship W2890788829A5010204267 @default.
- W2890788829 hasAuthorship W2890788829A5046805800 @default.
- W2890788829 hasAuthorship W2890788829A5051332325 @default.
- W2890788829 hasAuthorship W2890788829A5078141810 @default.
- W2890788829 hasBestOaLocation W28907888292 @default.
- W2890788829 hasConcept C106131492 @default.
- W2890788829 hasConcept C108010975 @default.
- W2890788829 hasConcept C11413529 @default.
- W2890788829 hasConcept C14036430 @default.
- W2890788829 hasConcept C153180895 @default.
- W2890788829 hasConcept C154945302 @default.
- W2890788829 hasConcept C155512373 @default.
- W2890788829 hasConcept C164866538 @default.
- W2890788829 hasConcept C199360897 @default.
- W2890788829 hasConcept C31972630 @default.
- W2890788829 hasConcept C41008148 @default.
- W2890788829 hasConcept C50644808 @default.
- W2890788829 hasConcept C6557445 @default.
- W2890788829 hasConcept C73555534 @default.
- W2890788829 hasConcept C78458016 @default.
- W2890788829 hasConcept C86803240 @default.
- W2890788829 hasConceptScore W2890788829C106131492 @default.
- W2890788829 hasConceptScore W2890788829C108010975 @default.
- W2890788829 hasConceptScore W2890788829C11413529 @default.
- W2890788829 hasConceptScore W2890788829C14036430 @default.
- W2890788829 hasConceptScore W2890788829C153180895 @default.
- W2890788829 hasConceptScore W2890788829C154945302 @default.
- W2890788829 hasConceptScore W2890788829C155512373 @default.
- W2890788829 hasConceptScore W2890788829C164866538 @default.
- W2890788829 hasConceptScore W2890788829C199360897 @default.
- W2890788829 hasConceptScore W2890788829C31972630 @default.
- W2890788829 hasConceptScore W2890788829C41008148 @default.
- W2890788829 hasConceptScore W2890788829C50644808 @default.
- W2890788829 hasConceptScore W2890788829C6557445 @default.
- W2890788829 hasConceptScore W2890788829C73555534 @default.
- W2890788829 hasConceptScore W2890788829C78458016 @default.
- W2890788829 hasConceptScore W2890788829C86803240 @default.
- W2890788829 hasLocation W28907888291 @default.
- W2890788829 hasLocation W28907888292 @default.
- W2890788829 hasOpenAccess W2890788829 @default.
- W2890788829 hasPrimaryLocation W28907888291 @default.
- W2890788829 hasRelatedWork W1490470283 @default.
- W2890788829 hasRelatedWork W1549839916 @default.
- W2890788829 hasRelatedWork W2033914206 @default.
- W2890788829 hasRelatedWork W2146076056 @default.
- W2890788829 hasRelatedWork W2326122716 @default.
- W2890788829 hasRelatedWork W2386387936 @default.
- W2890788829 hasRelatedWork W2809253131 @default.
- W2890788829 hasRelatedWork W2899084033 @default.
- W2890788829 hasRelatedWork W3047144510 @default.
- W2890788829 hasRelatedWork W3094412894 @default.
- W2890788829 isParatext "false" @default.
- W2890788829 isRetracted "false" @default.
- W2890788829 magId "2890788829" @default.
- W2890788829 workType "article" @default.