FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310071937> ?p ?o ?g. }

• W4310071937 endingPage "109856" @default.
• W4310071937 startingPage "109856" @default.
• W4310071937 abstract "Convolutional neural networks (CNNs) play a crucial role and achieve top results in computer vision tasks but at the cost of high computational cost and storage complexity. One way to solve this problem is the approximation of the convolution kernel using tensor decomposition methods. In this way, the original kernel is replaced with a sequence of kernels in a lower-dimensional space. This study proposes a novel CNN compression technique based on the hierarchical Tucker-2 (HT-2) tensor decomposition and makes an important contribution to the field of neural network compression based on low-rank approximations. We demonstrate the effectiveness of our approach on many CNN architectures on CIFAR-10 and ImageNet datasets. The obtained results show a significant reduction in parameters and FLOPS with a minor drop in classification accuracy. Compared to different state-of-the-art compression methods, including pruning and matrix/tensor decomposition, the HT-2, as a new alternative, outperforms most of the cited methods. The implementation of the proposed approach is very straightforward and can be easily coded in every deep learning library." @default.
• W4310071937 created "2022-11-30" @default.
• W4310071937 creator A5022656662 @default.
• W4310071937 creator A5030600070 @default.
• W4310071937 date "2023-01-01" @default.
• W4310071937 modified "2023-10-18" @default.
• W4310071937 title "Compressing convolutional neural networks with hierarchical Tucker-2 decomposition" @default.
• W4310071937 cites W1901129140 @default.
• W4310071937 cites W1903029394 @default.
• W4310071937 cites W1963826206 @default.
• W4310071937 cites W1993482030 @default.
• W4310071937 cites W2000215628 @default.
• W4310071937 cites W2024165284 @default.
• W4310071937 cites W2088025933 @default.
• W4310071937 cites W2097117768 @default.
• W4310071937 cites W2104636679 @default.
• W4310071937 cites W2113325037 @default.
• W4310071937 cites W2117539524 @default.
• W4310071937 cites W2194775991 @default.
• W4310071937 cites W2300242332 @default.
• W4310071937 cites W2475287302 @default.
• W4310071937 cites W2516041031 @default.
• W4310071937 cites W2568772110 @default.
• W4310071937 cites W2570702650 @default.
• W4310071937 cites W2580834719 @default.
• W4310071937 cites W2604998962 @default.
• W4310071937 cites W2617994470 @default.
• W4310071937 cites W2789142637 @default.
• W4310071937 cites W2807961551 @default.
• W4310071937 cites W2808168148 @default.
• W4310071937 cites W2886117254 @default.
• W4310071937 cites W2919115771 @default.
• W4310071937 cites W2924515500 @default.
• W4310071937 cites W2928560789 @default.
• W4310071937 cites W2945335799 @default.
• W4310071937 cites W2947963429 @default.
• W4310071937 cites W2960833983 @default.
• W4310071937 cites W2962956675 @default.
• W4310071937 cites W2963037989 @default.
• W4310071937 cites W2963145730 @default.
• W4310071937 cites W2963150697 @default.
• W4310071937 cites W2963223345 @default.
• W4310071937 cites W2963363373 @default.
• W4310071937 cites W2963446712 @default.
• W4310071937 cites W2964233199 @default.
• W4310071937 cites W2964266063 @default.
• W4310071937 cites W2965132998 @default.
• W4310071937 cites W3013080934 @default.
• W4310071937 cites W3018835489 @default.
• W4310071937 cites W3028304412 @default.
• W4310071937 cites W3034513523 @default.
• W4310071937 cites W3034633006 @default.
• W4310071937 cites W3035016149 @default.
• W4310071937 cites W3037399553 @default.
• W4310071937 cites W3133522500 @default.
• W4310071937 cites W3158688039 @default.
• W4310071937 cites W3205325461 @default.
• W4310071937 cites W3210033632 @default.
• W4310071937 cites W4200536695 @default.
• W4310071937 cites W4312900176 @default.
• W4310071937 doi "https://doi.org/10.1016/j.asoc.2022.109856" @default.
• W4310071937 hasPublicationYear "2023" @default.
• W4310071937 type Work @default.
• W4310071937 citedByCount "2" @default.
• W4310071937 countsByYear W43100719372023 @default.
• W4310071937 crossrefType "journal-article" @default.
• W4310071937 hasAuthorship W4310071937A5022656662 @default.
• W4310071937 hasAuthorship W4310071937A5030600070 @default.
• W4310071937 hasConcept C108010975 @default.
• W4310071937 hasConcept C108583219 @default.
• W4310071937 hasConcept C111335779 @default.
• W4310071937 hasConcept C11413529 @default.
• W4310071937 hasConcept C114614502 @default.
• W4310071937 hasConcept C124681953 @default.
• W4310071937 hasConcept C153180895 @default.
• W4310071937 hasConcept C154945302 @default.
• W4310071937 hasConcept C155281189 @default.
• W4310071937 hasConcept C164226766 @default.
• W4310071937 hasConcept C173608175 @default.
• W4310071937 hasConcept C18903297 @default.
• W4310071937 hasConcept C202444582 @default.
• W4310071937 hasConcept C2524010 @default.
• W4310071937 hasConcept C2986737658 @default.
• W4310071937 hasConcept C33923547 @default.
• W4310071937 hasConcept C3826847 @default.
• W4310071937 hasConcept C41008148 @default.
• W4310071937 hasConcept C42704193 @default.
• W4310071937 hasConcept C45347329 @default.
• W4310071937 hasConcept C50644808 @default.
• W4310071937 hasConcept C6557445 @default.
• W4310071937 hasConcept C74193536 @default.
• W4310071937 hasConcept C81363708 @default.
• W4310071937 hasConcept C86803240 @default.
• W4310071937 hasConceptScore W4310071937C108010975 @default.
• W4310071937 hasConceptScore W4310071937C108583219 @default.
• W4310071937 hasConceptScore W4310071937C111335779 @default.
• W4310071937 hasConceptScore W4310071937C11413529 @default.
• W4310071937 hasConceptScore W4310071937C114614502 @default.

• next