Knowledge Commons of Institute of Automation,CAS
Shift-Invariant Convolutional Network Search | |
Nannan Li1,2![]() ![]() ![]() ![]() | |
2020-07 | |
会议名称 | The International Joint Conference on Neural Networks |
会议日期 | 19-24 July |
会议地点 | Glasgow, United Kingdom |
摘要 | The development of Neural Architecture Search (NAS) makes the Convolutional Neural Networks (CNN) more diverse and effective. But previous NAS approaches don’t pay attention to the shift-invariant of CNN. Without the shift-invariant, convolutional network is not robust enough when data is disturbed or damaged. Besides, taking accuracy as the only optimization goal of NAS cannot meet the increasingly diverse needs. In this paper, we propose the Shift-Invariant Convolutional Network Search (SICNS). It uses one-shot NAS to search for shift-invariant convolutional network by incorporating the low-pass filter into the one-shot model. Furthermore, SICNS optimizes multiple indicators simultaneously through the multi-objective evolutionary algorithm. Through training one-shot model and evolving the architecture, we obtain convolutional networks which are robust and powerful on image classification task. Especially, our work can achieve 4.52% test error on CIFAR-10 with 0.7M parameters. And in case the input data are disturbed, the accuracy of searched network is 2.96% higher than network without low-pass filter. |
关键词 | Neural architecture search, shift-invariant, multi-objective, low-pass filter, image classification |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 强化与进化学习 |
国重实验室规划方向分类 | 智能计算与学习 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/40631 |
专题 | 多模态人工智能系统全国重点实验室_深度强化学习 |
通讯作者 | Yaran Chen |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.School of artificial intelligence, University of Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Nannan Li,Yaran Chen,Zixiang Ding,et al. Shift-Invariant Convolutional Network Search[C],2020. |
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 | ||
Shift-Invariant_Conv(1067KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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