Knowledge Commons of Institute of Automation,CAS
RENAS: Reinforced Evolutionary Neural Architecture Search | |
Chen, Yukang1; Meng, Gaofeng1; Zhang, Qian2; Xiang, Shiming1; Huang, Chang2; Mu, Lisen2; Wang, Xinggang3 | |
2019-06 | |
会议名称 | IEEE Conference on Computer Vision and Pattern Recognition |
页码 | 4787-4796 |
会议日期 | 2019-6-16 |
会议地点 | 美国洛杉矶长滩 |
摘要 | 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. |
收录类别 | EI |
资助项目 | Beijing 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] |
语种 | 英语 |
七大方向——子方向分类 | 目标检测、跟踪与识别 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/39088 |
专题 | 多模态人工智能系统全国重点实验室_先进时空数据分析与学习 |
作者单位 | 1.中科院自动化所 2.地平线机器人 3.华中科技大学 |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Chen, Yukang,Meng, Gaofeng,Zhang, Qian,et al. RENAS: Reinforced Evolutionary Neural Architecture Search[C],2019:4787-4796. |
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 | ||
RENAS- Reinforced Ev(1137KB) | 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