CASIA OpenIR  > 模式识别国家重点实验室  > 先进时空数据分析与学习
RENAS: Reinforced Evolutionary Neural Architecture Search
Chen, Yukang1; Meng, Gaofeng1; Zhang, Qian2; Xiang, Shiming1; Huang, Chang2; Mu, Lisen2; Wang, Xinggang3
2019-06
Conference NameIEEE Conference on Computer Vision and Pattern Recognition
Pages4787-4796
Conference Date2019-6-16
Conference Place美国洛杉矶长滩
Abstract

Neural Architecture Search (NAS) is an important yet challenging task in network design due to its high computational consumption. To address this issue, we propose the Reinforced Evolutionary Neural Architecture Search (RENAS), which is an evolutionary method with reinforced mutation for NAS. Our method integrates reinforced mutation into an evolution algorithm for neural architecture exploration, in which a mutation controller is introduced to learn the effects of slight modifications and make mutation actions. The reinforced mutation controller guides the model population to evolve efficiently. Furthermore, as child mod- els can inherit parameters from their parents during evolution, our method requires very limited computational resources. In experiments, we conduct the proposed search method on CIFAR-10 and obtain a powerful network architecture, RENASNet. This architecture achieves a competitive result on CIFAR-10. The explored network architecture is transferable to ImageNet and achieves a new state-of-the-art accuracy, i.e., 75.7% top-1 accuracy with 5.36M param- eters on mobile ImageNet. We further test its performance on semantic segmentation with DeepLabv3 on the PASCAL VOC. RENASNet outperforms MobileNet-v1, MobileNet-v2 and NASNet. It achieves 75.83% mIOU without being pre-trained on COCO.

Indexed ByEI
Funding ProjectBeijing Natural Science Foundation[L172053] ; National Natural Science Foundation of China[91646207] ; National Natural Science Foundation of China[61573352] ; National Natural Science Foundation of China[61773377] ; National Natural Science Foundation of China[61773377] ; National Natural Science Foundation of China[61573352] ; National Natural Science Foundation of China[91646207] ; Beijing Natural Science Foundation[L172053]
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/39088
Collection模式识别国家重点实验室_先进时空数据分析与学习
Affiliation1.中科院自动化所
2.地平线机器人
3.华中科技大学
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Chen, Yukang,Meng, Gaofeng,Zhang, Qian,et al. RENAS: Reinforced Evolutionary Neural Architecture Search[C],2019:4787-4796.
Files in This Item: Download All
File Name/Size DocType Version Access License
RENAS- Reinforced Ev(1137KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Chen, Yukang]'s Articles
[Meng, Gaofeng]'s Articles
[Zhang, Qian]'s Articles
Baidu academic
Similar articles in Baidu academic
[Chen, Yukang]'s Articles
[Meng, Gaofeng]'s Articles
[Zhang, Qian]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Chen, Yukang]'s Articles
[Meng, Gaofeng]'s Articles
[Zhang, Qian]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: RENAS- Reinforced Evolutionary Neural Architecture Search.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.