Matches in SemOpenAlex for { <https://semopenalex.org/work/W4224932523> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4224932523 abstract "Convolutional Neural Networks have been extensively used for solving many vision problems. However, due to high memory and computational requirements, deployment of these models on edge devices is limited. Many embedded friendly models such as MobileNet, ShuffleNet, SqueezeNet, and many more are proposed to serve this purpose. But these models are still not compact enough to deploy on edge devices. The popular metric-based pruning methods (which are aimed at pruning insignificant and redundant filters) could achieve limited compression for embedded friendly models such as MobileNet. In this paper, we propose a novel hybrid filter pruning method that prunes both redundant and insignificant filters at the same time. Additionally, we have designed custom regularizers that enable us to prune additional filters from convolutional layers. Pruning experiments are conducted on MobileNetv1 based Single-Shot Object Detector (SSD) for face detection problem. Through our experiments, we could prune 40.11% of parameters and reduce 67.03% of FLOPs from MobileNetv1 with a little drop in model performance (1.67 mAP on MS COCO). On an ARM-based edge device, the inference time is reduced from 198ms to 84ms." @default.
- W4224932523 created "2022-04-28" @default.
- W4224932523 creator A5068826431 @default.
- W4224932523 creator A5082635648 @default.
- W4224932523 creator A5090340316 @default.
- W4224932523 date "2022-05-23" @default.
- W4224932523 modified "2023-09-30" @default.
- W4224932523 title "A Simple Hybrid Filter Pruning for Efficient Edge Inference" @default.
- W4224932523 cites W2076063813 @default.
- W4224932523 cites W2285660444 @default.
- W4224932523 cites W2614986686 @default.
- W4224932523 cites W2808168148 @default.
- W4224932523 cites W2963566548 @default.
- W4224932523 cites W2989808579 @default.
- W4224932523 cites W3009383973 @default.
- W4224932523 cites W3013601111 @default.
- W4224932523 cites W3155145285 @default.
- W4224932523 doi "https://doi.org/10.1109/icassp43922.2022.9747152" @default.
- W4224932523 hasPublicationYear "2022" @default.
- W4224932523 type Work @default.
- W4224932523 citedByCount "1" @default.
- W4224932523 countsByYear W42249325232023 @default.
- W4224932523 crossrefType "proceedings-article" @default.
- W4224932523 hasAuthorship W4224932523A5068826431 @default.
- W4224932523 hasAuthorship W4224932523A5082635648 @default.
- W4224932523 hasAuthorship W4224932523A5090340316 @default.
- W4224932523 hasConcept C106131492 @default.
- W4224932523 hasConcept C108010975 @default.
- W4224932523 hasConcept C111919701 @default.
- W4224932523 hasConcept C11413529 @default.
- W4224932523 hasConcept C127413603 @default.
- W4224932523 hasConcept C138236772 @default.
- W4224932523 hasConcept C154945302 @default.
- W4224932523 hasConcept C162307627 @default.
- W4224932523 hasConcept C173608175 @default.
- W4224932523 hasConcept C176217482 @default.
- W4224932523 hasConcept C21547014 @default.
- W4224932523 hasConcept C2776214188 @default.
- W4224932523 hasConcept C2778456923 @default.
- W4224932523 hasConcept C31972630 @default.
- W4224932523 hasConcept C3826847 @default.
- W4224932523 hasConcept C41008148 @default.
- W4224932523 hasConcept C6557445 @default.
- W4224932523 hasConcept C79974875 @default.
- W4224932523 hasConcept C81363708 @default.
- W4224932523 hasConcept C86803240 @default.
- W4224932523 hasConceptScore W4224932523C106131492 @default.
- W4224932523 hasConceptScore W4224932523C108010975 @default.
- W4224932523 hasConceptScore W4224932523C111919701 @default.
- W4224932523 hasConceptScore W4224932523C11413529 @default.
- W4224932523 hasConceptScore W4224932523C127413603 @default.
- W4224932523 hasConceptScore W4224932523C138236772 @default.
- W4224932523 hasConceptScore W4224932523C154945302 @default.
- W4224932523 hasConceptScore W4224932523C162307627 @default.
- W4224932523 hasConceptScore W4224932523C173608175 @default.
- W4224932523 hasConceptScore W4224932523C176217482 @default.
- W4224932523 hasConceptScore W4224932523C21547014 @default.
- W4224932523 hasConceptScore W4224932523C2776214188 @default.
- W4224932523 hasConceptScore W4224932523C2778456923 @default.
- W4224932523 hasConceptScore W4224932523C31972630 @default.
- W4224932523 hasConceptScore W4224932523C3826847 @default.
- W4224932523 hasConceptScore W4224932523C41008148 @default.
- W4224932523 hasConceptScore W4224932523C6557445 @default.
- W4224932523 hasConceptScore W4224932523C79974875 @default.
- W4224932523 hasConceptScore W4224932523C81363708 @default.
- W4224932523 hasConceptScore W4224932523C86803240 @default.
- W4224932523 hasLocation W42249325231 @default.
- W4224932523 hasOpenAccess W4224932523 @default.
- W4224932523 hasPrimaryLocation W42249325231 @default.
- W4224932523 hasRelatedWork W12246666 @default.
- W4224932523 hasRelatedWork W13637491 @default.
- W4224932523 hasRelatedWork W1674447 @default.
- W4224932523 hasRelatedWork W268777 @default.
- W4224932523 hasRelatedWork W4136762 @default.
- W4224932523 hasRelatedWork W5143923 @default.
- W4224932523 hasRelatedWork W5879097 @default.
- W4224932523 hasRelatedWork W7842670 @default.
- W4224932523 hasRelatedWork W8203773 @default.
- W4224932523 hasRelatedWork W8451425 @default.
- W4224932523 isParatext "false" @default.
- W4224932523 isRetracted "false" @default.
- W4224932523 workType "article" @default.