.png){kind=icon}
.png){kind=icon}
Return
Efficient tensor decomposition-based filter pruning
.png){kind=icon}
OA
AI
DOI：10.1016/j.neunet.2024.106393.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In this paper, we present CORING, which is short for effiCient tensOr decomposition-based filteR prunING, a novel filter pruning methodology for neural networks. CORING is crafted to achieve efficient tensor decomposition-based pruning, a stark departure from conventional approaches that rely on vectorized or matricized filter representations. Our approach represents a significant leap forward in the field by introducing tensor decompositions, specifically the HOSVD, which preserves the multidimensional nature of filters while providing a low-rank approximation, thus substantially reducing complexity. Furthermore, we introduce a versatile method for calculating filter similarity by using the low-rank approximation offered by the HOSVD. This obviates the need for using full filters or reshaped versions and enhances the overall efficiency and effectiveness of our approach. Extensive experimentation across diverse architectures and datasets spanning various vision tasks, including image classification, object detection, instance segmentation, and keypoint detection, validates CORING's prowess. Remarkably, it outperforms state -of -the -art methods in reducing MACs and parameters, consistently enhancing validation accuracy. Furthermore, we supplement our quantitative results with a comprehensive ablation study, providing substantial evidence of the efficiency of our tensorbased approach. Beyond quantitative outcomes, qualitative results vividly illustrate CORING's ability to retain essential features within pruned neural networks. Our code is available for research purposes.
Keywords:
Network compression
Tensor decompositions
Filter pruning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.3
Papers:
7.8K
Citations:
3.0W