Matches in SemOpenAlex for { <https://semopenalex.org/work/W4221167908> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4221167908 abstract "The pursuit algorithms integrated in multi-layer convolutional sparse coding (ML-CSC) can interpret the convolutional neural networks (CNNs). However, many current state-of-art (SOTA) pursuit algorithms require multiple iterations to optimize the solution of ML-CSC, which limits their applications to deeper CNNs due to high computational cost and large number of resources for getting very tiny gain of performance. In this study, we focus on the 0th iteration in pursuit algorithm by introducing an effective initialization strategy for each layer, by which the solution for ML-CSC can be improved. Specifically, we first propose a novel width-depth synchronous extension-based basis pursuit (WSEBP) algorithm which solves the ML-CSC problem without the limitation of the number of iterations compared to the SOTA algorithms and maximizes the performance by an effective initialization in each layer. Then, we propose a simple and unified ML-CSC-based classification network (ML-CSC-Net) which consists of an ML-CSC-based feature encoder and a fully-connected layer to validate the performance of WSEBP on image classification task. The experimental results show that our proposed WSEBP outperforms SOTA algorithms in terms of accuracy and consumption resources. In addition, the WSEBP integrated in CNNs can improve the performance of deeper CNNs and make them interpretable. Finally, taking VGG as an example, we propose WSEBP-VGG13 to enhance the performance of VGG13, which achieves competitive results on four public datasets, i.e., 87.79% vs. 86.83% on Cifar-10 dataset, 58.01% vs. 54.60% on Cifar-100 dataset, 91.52% vs. 89.58% on COVID-19 dataset, and 99.88% vs. 99.78% on Crack dataset, respectively. The results show the effectiveness of the proposed WSEBP, the improved performance of ML-CSC with WSEBP, and interpretation of the CNNs or deeper CNNs." @default.
- W4221167908 created "2022-04-03" @default.
- W4221167908 creator A5001420988 @default.
- W4221167908 creator A5041620666 @default.
- W4221167908 creator A5046552547 @default.
- W4221167908 creator A5047632784 @default.
- W4221167908 creator A5055532928 @default.
- W4221167908 date "2022-03-28" @default.
- W4221167908 modified "2023-09-26" @default.
- W4221167908 title "WSEBP: A Novel Width-depth Synchronous Extension-based Basis Pursuit Algorithm for Multi-Layer Convolutional Sparse Coding" @default.
- W4221167908 doi "https://doi.org/10.48550/arxiv.2203.14856" @default.
- W4221167908 hasPublicationYear "2022" @default.
- W4221167908 type Work @default.
- W4221167908 citedByCount "0" @default.
- W4221167908 crossrefType "posted-content" @default.
- W4221167908 hasAuthorship W4221167908A5001420988 @default.
- W4221167908 hasAuthorship W4221167908A5041620666 @default.
- W4221167908 hasAuthorship W4221167908A5046552547 @default.
- W4221167908 hasAuthorship W4221167908A5047632784 @default.
- W4221167908 hasAuthorship W4221167908A5055532928 @default.
- W4221167908 hasBestOaLocation W42211679081 @default.
- W4221167908 hasConcept C105795698 @default.
- W4221167908 hasConcept C111919701 @default.
- W4221167908 hasConcept C11413529 @default.
- W4221167908 hasConcept C114466953 @default.
- W4221167908 hasConcept C118505674 @default.
- W4221167908 hasConcept C138885662 @default.
- W4221167908 hasConcept C153180895 @default.
- W4221167908 hasConcept C154945302 @default.
- W4221167908 hasConcept C178790620 @default.
- W4221167908 hasConcept C179518139 @default.
- W4221167908 hasConcept C185592680 @default.
- W4221167908 hasConcept C199360897 @default.
- W4221167908 hasConcept C2776401178 @default.
- W4221167908 hasConcept C2778029271 @default.
- W4221167908 hasConcept C2779227376 @default.
- W4221167908 hasConcept C33923547 @default.
- W4221167908 hasConcept C41008148 @default.
- W4221167908 hasConcept C41895202 @default.
- W4221167908 hasConcept C81363708 @default.
- W4221167908 hasConceptScore W4221167908C105795698 @default.
- W4221167908 hasConceptScore W4221167908C111919701 @default.
- W4221167908 hasConceptScore W4221167908C11413529 @default.
- W4221167908 hasConceptScore W4221167908C114466953 @default.
- W4221167908 hasConceptScore W4221167908C118505674 @default.
- W4221167908 hasConceptScore W4221167908C138885662 @default.
- W4221167908 hasConceptScore W4221167908C153180895 @default.
- W4221167908 hasConceptScore W4221167908C154945302 @default.
- W4221167908 hasConceptScore W4221167908C178790620 @default.
- W4221167908 hasConceptScore W4221167908C179518139 @default.
- W4221167908 hasConceptScore W4221167908C185592680 @default.
- W4221167908 hasConceptScore W4221167908C199360897 @default.
- W4221167908 hasConceptScore W4221167908C2776401178 @default.
- W4221167908 hasConceptScore W4221167908C2778029271 @default.
- W4221167908 hasConceptScore W4221167908C2779227376 @default.
- W4221167908 hasConceptScore W4221167908C33923547 @default.
- W4221167908 hasConceptScore W4221167908C41008148 @default.
- W4221167908 hasConceptScore W4221167908C41895202 @default.
- W4221167908 hasConceptScore W4221167908C81363708 @default.
- W4221167908 hasLocation W42211679081 @default.
- W4221167908 hasOpenAccess W4221167908 @default.
- W4221167908 hasPrimaryLocation W42211679081 @default.
- W4221167908 hasRelatedWork W2175746458 @default.
- W4221167908 hasRelatedWork W2613736958 @default.
- W4221167908 hasRelatedWork W2732542196 @default.
- W4221167908 hasRelatedWork W2738221750 @default.
- W4221167908 hasRelatedWork W2760085659 @default.
- W4221167908 hasRelatedWork W2883200793 @default.
- W4221167908 hasRelatedWork W2912288872 @default.
- W4221167908 hasRelatedWork W2940661641 @default.
- W4221167908 hasRelatedWork W3012978760 @default.
- W4221167908 hasRelatedWork W3093612317 @default.
- W4221167908 isParatext "false" @default.
- W4221167908 isRetracted "false" @default.
- W4221167908 workType "article" @default.