Knowledge Commons of Institute of Automation,CAS
Multi-Objective Neural Architecture Search for Light-Weight Model | |
Nannan Li1,2; Yaran Chen1,2; Zixiang Ding1,2; Dongbin Zhao1,2; Zhonghua Pang3; Ruisheng Qin3 | |
2019-11 | |
会议名称 | 2019 Chinese Automation Congress (CAC) |
会议日期 | 22-24 November 2019 |
会议地点 | Hangzhou, China |
摘要 | Neural architecture search (NAS) has achieved superior performance in visual tasks by automatically designing an effective neural network architecture. In recent years, deep neural networks are increasingly applied to resource-constrained devices. As a result, in addition to the model performance, model size is another very important factor that requires to consider when designing powerful neural network architectures. Therefore, we propose the multi-objective neural architecture search for light-weight model and name it Light-weight NAS. On one hand, the Light-weight NAS introduces Multiply-ACcumulate (MAC) into the optimize objective to get the architecture with fewer parameters. On the other hand, we simplify the search space and adopt weight sharing to make the search process more efficient. Experimental results indicate that the searched architecture can perform competitive classification accuracy with few parameters on the image classification task, while using less computation cost than the most existing multi-objective NAS approaches. |
关键词 | Neural architecture search light-weight multi-objective reinforcement learning image classification |
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/173211/52189 |
专题 | 多模态人工智能系统全国重点实验室_深度强化学习 |
作者单位 | 1.State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences 2.School of artificial intelligence, University of Chinese Academy of Sciences 3.Key Laboratory of Fieldbus Technology and Automation of Beijing North China University of Technology |
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 | Nannan Li,Yaran Chen,Zixiang Ding,et al. Multi-Objective Neural Architecture Search for Light-Weight Model[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-Objective_Neur(430KB) | 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