FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2969662912> ?p ?o ?g. }

• W2969662912 abstract "Convolutional neural networks (CNNs) based solutions have achieved state-of-the-art performances for many computer vision tasks, including classification and super-resolution of images. Usually the success of these methods comes with a cost of millions of parameters due to stacking deep convolutional layers. Moreover, quite a large number of filters are also used for a single convolutional layer, which exaggerates the parameter burden of current methods. Thus, in this paper, we try to reduce the number of parameters of CNNs by learning a basis of the filters in convolutional layers. For the forward pass, the learned basis is used to approximate the original filters and then used as parameters for the convolutional layers. We validate our proposed solution for multiple CNN architectures on image classification and image super-resolution benchmarks and compare favorably to the existing state-of-the-art in terms of reduction of parameters and preservation of accuracy." @default.
• W2969662912 created "2019-08-29" @default.
• W2969662912 creator A5001254143 @default.
• W2969662912 creator A5036891682 @default.
• W2969662912 creator A5052236177 @default.
• W2969662912 creator A5071547746 @default.
• W2969662912 date "2019-08-23" @default.
• W2969662912 modified "2023-10-16" @default.
• W2969662912 title "Learning Filter Basis for Convolutional Neural Network Compression" @default.
• W2969662912 cites W1522301498 @default.
• W2969662912 cites W1536680647 @default.
• W2969662912 cites W1686810756 @default.
• W2969662912 cites W1791560514 @default.
• W2969662912 cites W1903029394 @default.
• W2969662912 cites W1930824406 @default.
• W2969662912 cites W1996901117 @default.
• W2969662912 cites W2047920195 @default.
• W2969662912 cites W2102605133 @default.
• W2969662912 cites W2104636679 @default.
• W2969662912 cites W2121927366 @default.
• W2969662912 cites W2131524184 @default.
• W2969662912 cites W2163605009 @default.
• W2969662912 cites W2167215970 @default.
• W2969662912 cites W2172166488 @default.
• W2969662912 cites W2194775991 @default.
• W2969662912 cites W2242218935 @default.
• W2969662912 cites W2300242332 @default.
• W2969662912 cites W2319920447 @default.
• W2969662912 cites W2402144811 @default.
• W2969662912 cites W2405920868 @default.
• W2969662912 cites W2474628748 @default.
• W2969662912 cites W2508457857 @default.
• W2969662912 cites W2520760693 @default.
• W2969662912 cites W2554931888 @default.
• W2969662912 cites W2557641257 @default.
• W2969662912 cites W2560017826 @default.
• W2969662912 cites W2593245696 @default.
• W2969662912 cites W2613155248 @default.
• W2969662912 cites W2613718673 @default.
• W2969662912 cites W2741137940 @default.
• W2969662912 cites W2883028206 @default.
• W2969662912 cites W2884371179 @default.
• W2969662912 cites W2886851211 @default.
• W2969662912 cites W2894581376 @default.
• W2969662912 cites W2899771611 @default.
• W2969662912 cites W2913182483 @default.
• W2969662912 cites W2955123570 @default.
• W2969662912 cites W2962851801 @default.
• W2969662912 cites W2962956675 @default.
• W2969662912 cites W2963000224 @default.
• W2969662912 cites W2963037989 @default.
• W2969662912 cites W2963114950 @default.
• W2969662912 cites W2963363373 @default.
• W2969662912 cites W2963372104 @default.
• W2969662912 cites W2963419583 @default.
• W2969662912 cites W2963446712 @default.
• W2969662912 cites W2963674932 @default.
• W2969662912 cites W2964178216 @default.
• W2969662912 cites W2964299589 @default.
• W2969662912 cites W2966256598 @default.
• W2969662912 cites W2968025890 @default.
• W2969662912 cites W3118608800 @default.
• W2969662912 cites W54257720 @default.
• W2969662912 doi "https://doi.org/10.48550/arxiv.1908.08932" @default.
• W2969662912 hasPublicationYear "2019" @default.
• W2969662912 type Work @default.
• W2969662912 sameAs 2969662912 @default.
• W2969662912 citedByCount "1" @default.
• W2969662912 countsByYear W29696629122021 @default.
• W2969662912 crossrefType "posted-content" @default.
• W2969662912 hasAuthorship W2969662912A5001254143 @default.
• W2969662912 hasAuthorship W2969662912A5036891682 @default.
• W2969662912 hasAuthorship W2969662912A5052236177 @default.
• W2969662912 hasAuthorship W2969662912A5071547746 @default.
• W2969662912 hasBestOaLocation W29696629121 @default.
• W2969662912 hasConcept C106131492 @default.
• W2969662912 hasConcept C108583219 @default.
• W2969662912 hasConcept C111335779 @default.
• W2969662912 hasConcept C11413529 @default.
• W2969662912 hasConcept C12426560 @default.
• W2969662912 hasConcept C153180895 @default.
• W2969662912 hasConcept C154945302 @default.
• W2969662912 hasConcept C157899210 @default.
• W2969662912 hasConcept C2524010 @default.
• W2969662912 hasConcept C31972630 @default.
• W2969662912 hasConcept C33923547 @default.
• W2969662912 hasConcept C41008148 @default.
• W2969662912 hasConcept C57273362 @default.
• W2969662912 hasConcept C81363708 @default.
• W2969662912 hasConceptScore W2969662912C106131492 @default.
• W2969662912 hasConceptScore W2969662912C108583219 @default.
• W2969662912 hasConceptScore W2969662912C111335779 @default.
• W2969662912 hasConceptScore W2969662912C11413529 @default.
• W2969662912 hasConceptScore W2969662912C12426560 @default.
• W2969662912 hasConceptScore W2969662912C153180895 @default.
• W2969662912 hasConceptScore W2969662912C154945302 @default.
• W2969662912 hasConceptScore W2969662912C157899210 @default.
• W2969662912 hasConceptScore W2969662912C2524010 @default.
• W2969662912 hasConceptScore W2969662912C31972630 @default.
• W2969662912 hasConceptScore W2969662912C33923547 @default.

• next