.png){kind=icon}
返回
Soft independence guided filter pruning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2024.110488.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Filter pruning (FP) is an effective method for reducing the computational costs of convolutional neural networks, and herein, the most critical task involves evaluating the significance of each convolutional filter and eliminating the less important ones while minimizing performance degradation. Most existing FP methods consider only local information, which may prevent them from accurately recognizing the most important filters. To address this limitation, we propose the soft filter independence (SFI) method, which leverages global information to identify the most important filters using their magnitude and correlation information in different functional layers. The SFI criterion measures the replaceability of filters from a global perspective in a network. Filters with low independence can be represented effectively by others, so their information can be accurately conveyed by other filters. In addition, we introduce a novel SFI-based asymptotic pruning ratio, which improves training and pruning stability. Compared to the most advanced FP methods, our method enables CNNs to achieve higher pruning rates and better classification performance.
Keyword:
Convolutional neural networks
Filter pruning
Filter independence
期刊
IF:
7.6
论文数:
1.4W
被引数:
4.9W
机构
引用论文
Ethics Experts as an Instrument of Technocratic Governance: Evidence from EU Medical Biotechnology Policy.png)
Governance
GovernanceIF0
PREAI
分享收藏A slice of π : An exploratory neuroimaging study of digit encoding and retrieval in a superior memoristNeurocase
OAAI
NeurocaseIF0
OAAI分享收藏AutoPruner: An end-to-end trainable filter pruning method for efficient deep model inferenceAutoPruner: 一种用于高效深度模型推理的端到端可训练滤波器修剪方法PATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏
查看更多内容