FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201158165> ?p ?o ?g. }

• W3201158165 abstract "Automated Machine Learning(Auto-ML) pruning methods aim at searching a pruning strategy automatically to reduce the computational complexity of deep Convolutional Neural Networks(deep CNNs). However, some previous work found that the results of many Auto-ML pruning methods cannot even surpass the results of the uniformly pruning method. In this paper, the ineffectiveness of Auto-ML pruning which is caused by unfull and unfair training of the supernet is shown. A deep supernet suffers from unfull training because it contains too many candidates. To overcome the unfull training, a stage-wise pruning(SWP) method is proposed, which splits a deep supernet into several stage-wise supernets to reduce the candidate number and utilize inplace distillation to supervise the stage training. Besides, A wide supernet is hit by unfair training since the sampling probability of each channel is unequal. Therefore, the fullnet and the tinynet are sampled in each training iteration to ensure each channel can be overtrained. Remarkably, the proxy performance of the subnets trained with SWP is closer to the actual performance than that of most of the previous Auto-ML pruning work. Experiments show that SWP achieves the state-of-the-art on both CIFAR-10 and ImageNet under the mobile setting." @default.
• W3201158165 created "2021-09-27" @default.
• W3201158165 creator A5062400907 @default.
• W3201158165 creator A5070244885 @default.
• W3201158165 creator A5071466474 @default.
• W3201158165 creator A5072320394 @default.
• W3201158165 date "2020-11-10" @default.
• W3201158165 modified "2023-09-27" @default.
• W3201158165 title "Effective Model Compression via Stage-wise Pruning" @default.
• W3201158165 cites W1821462560 @default.
• W3201158165 cites W2117539524 @default.
• W3201158165 cites W2194775991 @default.
• W3201158165 cites W2553303224 @default.
• W3201158165 cites W2612445135 @default.
• W3201158165 cites W2739879705 @default.
• W3201158165 cites W2765390540 @default.
• W3201158165 cites W2785366763 @default.
• W3201158165 cites W2786054724 @default.
• W3201158165 cites W2788653909 @default.
• W3201158165 cites W2798603777 @default.
• W3201158165 cites W2808373772 @default.
• W3201158165 cites W2886851211 @default.
• W3201158165 cites W2887783173 @default.
• W3201158165 cites W2905741102 @default.
• W3201158165 cites W2924888702 @default.
• W3201158165 cites W2928560789 @default.
• W3201158165 cites W2932077855 @default.
• W3201158165 cites W2944355599 @default.
• W3201158165 cites W2946948417 @default.
• W3201158165 cites W2947681860 @default.
• W3201158165 cites W2951104886 @default.
• W3201158165 cites W2953604046 @default.
• W3201158165 cites W2958458355 @default.
• W3201158165 cites W2962835968 @default.
• W3201158165 cites W2962851801 @default.
• W3201158165 cites W2962965870 @default.
• W3201158165 cites W2963140066 @default.
• W3201158165 cites W2963163009 @default.
• W3201158165 cites W2963247446 @default.
• W3201158165 cites W2963363373 @default.
• W3201158165 cites W2963420686 @default.
• W3201158165 cites W2963446712 @default.
• W3201158165 cites W2963674932 @default.
• W3201158165 cites W2963918968 @default.
• W3201158165 cites W2964081807 @default.
• W3201158165 cites W2964118293 @default.
• W3201158165 cites W2964233199 @default.
• W3201158165 cites W2965658867 @default.
• W3201158165 cites W2976540144 @default.
• W3201158165 cites W2981698279 @default.
• W3201158165 cites W2981748264 @default.
• W3201158165 cites W2982083293 @default.
• W3201158165 cites W2984618279 @default.
• W3201158165 cites W2994749257 @default.
• W3201158165 cites W3016112239 @default.
• W3201158165 cites W3034513523 @default.
• W3201158165 cites W3034528892 @default.
• W3201158165 cites W3109212549 @default.
• W3201158165 hasPublicationYear "2020" @default.
• W3201158165 type Work @default.
• W3201158165 sameAs 3201158165 @default.
• W3201158165 citedByCount "0" @default.
• W3201158165 crossrefType "posted-content" @default.
• W3201158165 hasAuthorship W3201158165A5062400907 @default.
• W3201158165 hasAuthorship W3201158165A5070244885 @default.
• W3201158165 hasAuthorship W3201158165A5071466474 @default.
• W3201158165 hasAuthorship W3201158165A5072320394 @default.
• W3201158165 hasConcept C108010975 @default.
• W3201158165 hasConcept C108583219 @default.
• W3201158165 hasConcept C119857082 @default.
• W3201158165 hasConcept C153180895 @default.
• W3201158165 hasConcept C154945302 @default.
• W3201158165 hasConcept C41008148 @default.
• W3201158165 hasConcept C6557445 @default.
• W3201158165 hasConcept C81363708 @default.
• W3201158165 hasConcept C86803240 @default.
• W3201158165 hasConceptScore W3201158165C108010975 @default.
• W3201158165 hasConceptScore W3201158165C108583219 @default.
• W3201158165 hasConceptScore W3201158165C119857082 @default.
• W3201158165 hasConceptScore W3201158165C153180895 @default.
• W3201158165 hasConceptScore W3201158165C154945302 @default.
• W3201158165 hasConceptScore W3201158165C41008148 @default.
• W3201158165 hasConceptScore W3201158165C6557445 @default.
• W3201158165 hasConceptScore W3201158165C81363708 @default.
• W3201158165 hasConceptScore W3201158165C86803240 @default.
• W3201158165 hasLocation W32011581651 @default.
• W3201158165 hasOpenAccess W3201158165 @default.
• W3201158165 hasPrimaryLocation W32011581651 @default.
• W3201158165 hasRelatedWork W2041970025 @default.
• W3201158165 hasRelatedWork W2757143157 @default.
• W3201158165 hasRelatedWork W2913465187 @default.
• W3201158165 hasRelatedWork W2927322017 @default.
• W3201158165 hasRelatedWork W2969975953 @default.
• W3201158165 hasRelatedWork W2990081069 @default.
• W3201158165 hasRelatedWork W3036939803 @default.
• W3201158165 hasRelatedWork W3038185437 @default.
• W3201158165 hasRelatedWork W3080754330 @default.
• W3201158165 hasRelatedWork W3103329669 @default.
• W3201158165 hasRelatedWork W3109212549 @default.
• W3201158165 hasRelatedWork W3129699627 @default.

• next