PP-NAS: Searching for Plug-and-Play Blocks on Convolutional Neural Network
文献类型:会议论文
作者 | Shen, Biluo2,3; Xiao, Anqi2,3; Tian, Jie1,2,3; Hu, Zhenhua2,3 |
出版日期 | 2021-10-11 |
会议日期 | 11-17 October 2021 |
会议地点 | Montreal, BC, Canada |
DOI | 10.1109/ICCVW54120.2021.00045 |
英文摘要 | Multi-scale features are of great importance in modern convolutional neural networks and show consistent performance gains on many vision tasks. Therefore, many plug-and-play blocks are introduced to upgrade existing convolutional neural networks for stronger multi-scale representation ability. However, the design of plug-and-play blocks is getting more complex and these manually designed blocks are not optimal. In this work, we propose PP-NAS to develop plug-and-play blocks based on neural architecture search. Specifically, we design a new search space and develop the corresponding search algorithm. Extensive experiments on CIFAR10, CIFAR100, and ImageNet show that PP-NAS can find a series of novel blocks that outperform manually designed ones. Transfer learning results on representative computer vision tasks including object detection and semantic segmentation further verify the superiority of the PP-NAS over the state-of-the-art CNNs (e.g., ResNet, Res2Net). Our code will be made avaliable at https://github.com/sbl1996/PP-NAS. |
语种 | 英语 |
URL标识 | 查看原文 |
源URL | [http://ir.ia.ac.cn/handle/173211/48675] |
专题 | 自动化研究所_中国科学院分子影像重点实验室 |
通讯作者 | Tian, Jie; Hu, Zhenhua |
作者单位 | 1.Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, Beihang University 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.Beijing Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Shen, Biluo,Xiao, Anqi,Tian, Jie,et al. PP-NAS: Searching for Plug-and-Play Blocks on Convolutional Neural Network[C]. 见:. Montreal, BC, Canada. 11-17 October 2021. |
入库方式: OAI收割
来源:自动化研究所
其他版本
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。