CASIA OpenIR  > 模式识别国家重点实验室  > 先进时空数据分析与学习
DetNAS: Backbone Search for Object Detection
Chen, Yukang1; Yang, Tong2; Zhang, Xiangyu2; Meng, Gaofeng1; Xiao, Xinyu1; Sun, Jian2
2019-12
Conference NameNeural Information Processing Systems 2019
Conference Date2019-12-8
Conference Place加拿大温哥华
Abstract

Object detectors are usually equipped with backbone networks designed for image classification. It might be sub-optimal because of the gap between the tasks of image classification and object detection. In this work, we present DetNAS to use Neural Architecture Search (NAS) for the design of better backbones for object detection. It is non-trivial because detection training typically needs ImageNet pre-training while NAS systems require accuracies on the target detection task as supervisory signals. Based on the technique of one-shot supernet, which contains all possible networks in the search space, we propose a framework for backbone search on object detection. We train the supernet under the typical detector training schedule: ImageNet pre-training and detection fine-tuning. Then, the architecture search is performed on the trained supernet, using the detection task as the guidance. This framework makes NAS on backbones very efficient. In experiments, we show the effectiveness of DetNAS on various detectors, for instance, one-stage RetinaNet and the two-stage FPN. We empirically find that networks searched on object detec- tion shows consistent superiority compared to those searched on ImageNet classifi- cation. The resulting architecture achieves superior performance than hand-crafted networks on COCO with much less FLOPs complexity.

Indexed ByEI
Funding ProjectNational 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]
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/39089
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.旷视科技
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Chen, Yukang,Yang, Tong,Zhang, Xiangyu,et al. DetNAS: Backbone Search for Object Detection[C],2019.
Files in This Item: Download All
File Name/Size DocType Version Access License
DetNAS- Backbone Sea(1366KB)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
[Yang, Tong]'s Articles
[Zhang, Xiangyu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Chen, Yukang]'s Articles
[Yang, Tong]'s Articles
[Zhang, Xiangyu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Chen, Yukang]'s Articles
[Yang, Tong]'s Articles
[Zhang, Xiangyu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: DetNAS- Backbone Search for Object Detection.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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