.png){kind=icon}
返回
Feature flow regularization: Improving structured sparsity in deep neural networks
.png){kind=icon}
OA
AI
DOI：10.1016/j.neunet.2023.02.013.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Pruning is a model compression method that removes redundant parameters and accelerates the inference speed of deep neural networks (DNNs) while maintaining accuracy. Most available pruning methods impose various conditions on parameters or features directly. In this paper, we propose a simple and effective regularization strategy to improve the structured sparsity and structured pruning in DNNs from a new perspective of evolution of features. In particular, we consider the trajectories connecting features of adjacent hidden layers, namely feature flow. We propose feature flow regularization (FFR) to penalize the length and the total absolute curvature of the trajectories, which implicitly increases the structured sparsity of the parameters. The principle behind FFR is that short and straight trajectories will lead to an efficient network that avoids redundant parameters. Experiments on CIFAR-10 and ImageNet datasets show that FFR improves structured sparsity and achieves pruning results comparable to or even better than those state-of-the-art methods. (c) 2023 Elsevier Ltd. All rights reserved.
Keyword:
Deep neural networks
Structured pruning
Image classification
Regularization
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.3
论文数:
7.8K
被引数:
3.0W
机构
引用论文
Calcium-modulating cyclophilin ligand regulates membrane trafficking of postsynaptic GABAA receptorsOAAI
OAAI分享收藏Investigation of Ti mesh-supported anodes for direct borohydride fuel cells直接硼氢化物燃料电池用钛网支撑阳极的研究
PREAI
分享收藏分享收藏Developing Wind and/or Solar Powered Crop Irrigation Systems for the Great Plains为大平原开发风能和/或太阳能作物灌溉系统
PREAI
分享收藏Enhanced thermal desorption of chlorinated hydrocarbons by nanoscale zero-valent iron: the effect of in situ dechlorination.png)
RSC Advances
OAAI
RSC AdvancesIF0
OAAI分享收藏
查看更多内容