Knowledge Commons of Institute of Automation,CAS
MULTI-LOSS-AWARE CHANNEL PRUNING OF DEEP NETWORKS | |
Hu YM(胡一鸣) | |
2019 | |
会议名称 | International Conference on Image Processing |
会议日期 | 2019.9.23 |
会议地点 | 台湾,台北国际会议中心 |
摘要 | Channel pruning, which seeks to reduce the model size by removing redundant channels, is a popular solution for deep networks compression. Existing channel pruning methods usually conduct layer-wise channel selection by directly minimizing the reconstruction error of feature maps between the baseline model and the pruned one. However, they ignore the feature and semantic distributions within feature maps and real contribution of channels to the overall performance. In this paper, we propose a new channel pruning method by explicitly using both intermediate outputs of the baseline model and the classification loss of the pruned model to supervise layer-wise channel selection. Particularly, we introduce an additional loss to encode the differences in the feature and semantic distributions within feature maps between the baseline model and the pruned one. By considering the reconstruction error, the additional loss and the classification loss at the same time, our approach can significantly improve the performance of the pruned model. Comprehensive experiments on benchmark datasets demonstrate the effectiveness of the proposed method. |
收录类别 | EI |
资助项目 | National Natural Science Foundation of China[61673376] |
语种 | 英语 |
七大方向——子方向分类 | 机器学习 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44838 |
专题 | 中国科学院工业视觉智能装备工程实验室_精密感知与控制 |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.School of Computer and Control Engineering, University of Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Hu YM. MULTI-LOSS-AWARE CHANNEL PRUNING OF DEEP NETWORKS[C],2019. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
multi-loss aware cha(298KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
个性服务 |
推荐该条目 |
保存到收藏夹 |
查看访问统计 |
导出为Endnote文件 |
谷歌学术 |
谷歌学术中相似的文章 |
[Hu YM(胡一鸣)]的文章 |
百度学术 |
百度学术中相似的文章 |
[Hu YM(胡一鸣)]的文章 |
必应学术 |
必应学术中相似的文章 |
[Hu YM(胡一鸣)]的文章 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论