Matches in SemOpenAlex for { <https://semopenalex.org/work/W3044461098> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W3044461098 endingPage "1209" @default.
- W3044461098 startingPage "1209" @default.
- W3044461098 abstract "Despite the great success of Convolutional Neural Networks (CNNs) in various visual recognition tasks, the high computational and storage costs of such deep networks impede their deployments in real-time remote sensing tasks. To this end, considerable attention has been given to the filter pruning techniques, which enable slimming deep networks with acceptable performance drops and thus implementing them on the remote sensing devices. In this paper, we propose a new scheme, termed Pruning Filter with Attention Mechanism (PFAM), to compress and accelerate traditional CNNs. In particular, a novel correlation-based filter pruning criterion, which explores the long-range dependencies among filters via an attention module, is employed to select the to-be-pruned filters. Distinct from previous methods, the less correlated filters are first pruned after the pruning stage in the current training epoch, and they are reconstructed and updated during the next training epoch. Doing so allows manipulating input data with the maximum information preserved when executing the original training strategy such that the compressed network model can be obtained without the need for the pretrained model. The proposed method is evaluated on three public remote sensing image datasets, and the experimental results demonstrate its superiority, compared to state-of-the-art baselines. Specifically, PFAM achieves a 0.67% accuracy improvement with a 40% model-size reduction on the Aerial Image Dataset (AID) dataset, which is impressive." @default.
- W3044461098 created "2020-07-29" @default.
- W3044461098 creator A5032503755 @default.
- W3044461098 creator A5046605531 @default.
- W3044461098 creator A5059068585 @default.
- W3044461098 creator A5082924617 @default.
- W3044461098 date "2020-07-27" @default.
- W3044461098 modified "2023-10-18" @default.
- W3044461098 title "Pruning Convolutional Neural Networks with an Attention Mechanism for Remote Sensing Image Classification" @default.
- W3044461098 cites W1958291604 @default.
- W3044461098 cites W2121480571 @default.
- W3044461098 cites W2146882684 @default.
- W3044461098 cites W2538244214 @default.
- W3044461098 cites W2650426111 @default.
- W3044461098 cites W2769165247 @default.
- W3044461098 cites W2770189358 @default.
- W3044461098 cites W2883111419 @default.
- W3044461098 cites W2897841402 @default.
- W3044461098 cites W2900790473 @default.
- W3044461098 cites W2919352650 @default.
- W3044461098 cites W3008381818 @default.
- W3044461098 cites W3011156941 @default.
- W3044461098 cites W3013515824 @default.
- W3044461098 cites W3103856189 @default.
- W3044461098 cites W3105577662 @default.
- W3044461098 doi "https://doi.org/10.3390/electronics9081209" @default.
- W3044461098 hasPublicationYear "2020" @default.
- W3044461098 type Work @default.
- W3044461098 sameAs 3044461098 @default.
- W3044461098 citedByCount "20" @default.
- W3044461098 countsByYear W30444610982020 @default.
- W3044461098 countsByYear W30444610982021 @default.
- W3044461098 countsByYear W30444610982022 @default.
- W3044461098 countsByYear W30444610982023 @default.
- W3044461098 crossrefType "journal-article" @default.
- W3044461098 hasAuthorship W3044461098A5032503755 @default.
- W3044461098 hasAuthorship W3044461098A5046605531 @default.
- W3044461098 hasAuthorship W3044461098A5059068585 @default.
- W3044461098 hasAuthorship W3044461098A5082924617 @default.
- W3044461098 hasBestOaLocation W30444610981 @default.
- W3044461098 hasConcept C106131492 @default.
- W3044461098 hasConcept C108010975 @default.
- W3044461098 hasConcept C108583219 @default.
- W3044461098 hasConcept C111335779 @default.
- W3044461098 hasConcept C119857082 @default.
- W3044461098 hasConcept C124101348 @default.
- W3044461098 hasConcept C153180895 @default.
- W3044461098 hasConcept C154945302 @default.
- W3044461098 hasConcept C2524010 @default.
- W3044461098 hasConcept C31972630 @default.
- W3044461098 hasConcept C33923547 @default.
- W3044461098 hasConcept C41008148 @default.
- W3044461098 hasConcept C50644808 @default.
- W3044461098 hasConcept C6557445 @default.
- W3044461098 hasConcept C81363708 @default.
- W3044461098 hasConcept C86803240 @default.
- W3044461098 hasConceptScore W3044461098C106131492 @default.
- W3044461098 hasConceptScore W3044461098C108010975 @default.
- W3044461098 hasConceptScore W3044461098C108583219 @default.
- W3044461098 hasConceptScore W3044461098C111335779 @default.
- W3044461098 hasConceptScore W3044461098C119857082 @default.
- W3044461098 hasConceptScore W3044461098C124101348 @default.
- W3044461098 hasConceptScore W3044461098C153180895 @default.
- W3044461098 hasConceptScore W3044461098C154945302 @default.
- W3044461098 hasConceptScore W3044461098C2524010 @default.
- W3044461098 hasConceptScore W3044461098C31972630 @default.
- W3044461098 hasConceptScore W3044461098C33923547 @default.
- W3044461098 hasConceptScore W3044461098C41008148 @default.
- W3044461098 hasConceptScore W3044461098C50644808 @default.
- W3044461098 hasConceptScore W3044461098C6557445 @default.
- W3044461098 hasConceptScore W3044461098C81363708 @default.
- W3044461098 hasConceptScore W3044461098C86803240 @default.
- W3044461098 hasIssue "8" @default.
- W3044461098 hasLocation W30444610981 @default.
- W3044461098 hasLocation W30444610982 @default.
- W3044461098 hasLocation W30444610983 @default.
- W3044461098 hasLocation W30444610984 @default.
- W3044461098 hasOpenAccess W3044461098 @default.
- W3044461098 hasPrimaryLocation W30444610981 @default.
- W3044461098 hasRelatedWork W2731899572 @default.
- W3044461098 hasRelatedWork W2999805992 @default.
- W3044461098 hasRelatedWork W3116150086 @default.
- W3044461098 hasRelatedWork W3133861977 @default.
- W3044461098 hasRelatedWork W4200173597 @default.
- W3044461098 hasRelatedWork W4223943233 @default.
- W3044461098 hasRelatedWork W4291897433 @default.
- W3044461098 hasRelatedWork W4312417841 @default.
- W3044461098 hasRelatedWork W4321369474 @default.
- W3044461098 hasRelatedWork W4380075502 @default.
- W3044461098 hasVolume "9" @default.
- W3044461098 isParatext "false" @default.
- W3044461098 isRetracted "false" @default.
- W3044461098 magId "3044461098" @default.
- W3044461098 workType "article" @default.