| Full text | |
| Author(s): |
Total Authors: 3
|
| Affiliation: | [1] Univ Estadual Campinas, Campinas - Brazil
Total Affiliations: 1
|
| Document type: | Journal article |
| Source: | PATTERN RECOGNITION LETTERS; v. 150, p. 235-241, OCT 2021. |
| Web of Science Citations: | 0 |
| Abstract | |
Kernel pruning methods have been proposed to speed up (simplify) convolutional neural network (CNN) models. However, the effectiveness of a simplified model is often below the original one. This letter presents new methods based on objective and subjective relevance criteria for kernel elimination in a layer-by-layer fashion. During the process, a CNN model is retrained only when the current layer is en-tirely simplified by adjusting the weights from the next layer to the first one and preserving weights of subsequent layers not involved in the process. We call this strategy progressive retraining, differently from kernel pruning methods that usually retrain the entire model after eliminating one or a few ker-nels. Our subjective relevance criterion exploits humans' ability to recognize visual patterns and improve the designer's understanding of the simplification process. We show that our methods can increase ef-fectiveness with considerable model simplification, outperforming two popular approaches and another one from the state-of-the-art on four challenging image datasets. An indirect comparison with 14 recent methods on a famous image dataset also places our approach using the objective criterion among the most competitive ones. (c) 2021 Elsevier B.V. All rights reserved. (AU) | |
| FAPESP's process: | 14/12236-1 - AnImaLS: Annotation of Images in Large Scale: what can machines and specialists learn from interaction? |
| Grantee: | Alexandre Xavier Falcão |
| Support Opportunities: | Research Projects - Thematic Grants |
| FAPESP's process: | 17/12974-0 - Multidimensional data visualization guided by machine learning |
| Grantee: | Daniel Osaku |
| Support Opportunities: | Scholarships in Brazil - Post-Doctoral |