Knowledge Commons of Institute of Automation,CAS
Improving One-Shot NAS with Shrinking-and-Expanding Supernet | |
Hu YM(胡一鸣)![]() | |
发表期刊 | Pattern Recognition
![]() |
2021-05-24 | |
卷号 | 118期号:0页码:0 |
文章类型 | SCI |
摘要 | Training a supernet using a copy of shared weights has become a popular approach to speed up neural ar- chitecture search (NAS). However, it is difficult for supernet to accurately evaluate on a large-scale search space due to high weight coupling in weight-sharing setting. To address this, we present a shrinking- and-expanding supernet that decouples the shared parameters by reducing the degree of weight shar- ing, avoiding unstable and inaccurate performance estimation as in previous methods. Specifically, we propose a new shrinking strategy that progressively simplifies the original search space by discarding unpromising operators in a smart way. Based on this, we further present an expanding strategy by ap- propriately increasing parameters of the shrunk supernet. We provide comprehensive evidences showing that, in weight-sharing supernet, the proposed method SE-NAS brings more accurate and more stable performance estimation. Experimental results on ImageNet dataset indicate that SE-NAS achieves higher Top-1 accuracy than its counterparts under the same complexity constraint and search space. The abla- tion study is presented to further understand SE-NAS. |
关键词 | Neural architecture search supernet Search space shrinking |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Natural Science Foundation of China[61673376] |
七大方向——子方向分类 | 机器学习 |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44836 |
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 Artificial Intelligence, University of Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Hu YM. Improving One-Shot NAS with Shrinking-and-Expanding Supernet[J]. Pattern Recognition,2021,118(0):0. |
APA | Hu YM.(2021).Improving One-Shot NAS with Shrinking-and-Expanding Supernet.Pattern Recognition,118(0),0. |
MLA | Hu YM."Improving One-Shot NAS with Shrinking-and-Expanding Supernet".Pattern Recognition 118.0(2021):0. |
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 | ||
Improving One-Shot N(1755KB) | 期刊论文 | 作者接受稿 | 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