AutoDet: Pyramid Network Architecture Search for Object Detection | |
Li, Zhihang1,2![]() ![]() | |
发表期刊 | INTERNATIONAL JOURNAL OF COMPUTER VISION
![]() |
ISSN | 0920-5691 |
2021-01-06 | |
期号 | 4页码:1087-1105 |
摘要 | Feature pyramids have delivered significant improvement in object detection. However, building effective feature pyramids heavily relies on expert knowledge, and also requires strenuous efforts to balance effectiveness and efficiency. Automatic search methods, such as NAS-FPN, automates the design of feature pyramids, but the low search efficiency makes it difficult to apply in a large search space. In this paper, we propose a novel search framework for a feature pyramid network, called AutoDet, which enables to automatic discovery of informative connections between multi-scale features and configure detection architectures with both high efficiency and state-of-the-art performance. In AutoDet, a new search space is specifically designed for feature pyramids in object detectors, which is more general than NAS-FPN. Furthermore, the architecture search process is formulated as a combinatorial optimization problem and solved by a Simulated Annealing-based Network Architecture Search method (SA-NAS). Compared with existing NAS methods, AutoDet ensures a dramatic reduction in search times. For example, our SA-NAS can be up to 30x faster than reinforcement learning-based approaches. Furthermore, AutoDet is compatible with both one-stage and two-stage structures with all kinds of backbone networks. We demonstrate the effectiveness of AutoDet with outperforming single-model results on the COCO dataset. Without pre-training on OpenImages, AutoDet with the ResNet-101 backbone achieves an AP of 39.7 and 47.3 for one-stage and two-stage architectures, respectively, which surpass current state-of-the-art methods. |
关键词 | Object detection Neural architecture search Feature pyramids |
DOI | 10.1007/s11263-020-01415-x |
收录类别 | SCI |
语种 | 英语 |
资助项目 | Beijing Natural Science Foundation[JQ18017] ; National Natural Science Foundation of China[U20A20223] ; Youth Innovation Promotion Association CAS[Y201929] |
项目资助者 | Beijing Natural Science Foundation ; National Natural Science Foundation of China ; Youth Innovation Promotion Association CAS |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Artificial Intelligence |
WOS记录号 | WOS:000605541100007 |
出版者 | SPRINGER |
七大方向——子方向分类 | 目标检测、跟踪与识别 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/42563 |
专题 | 智能感知与计算研究中心 |
通讯作者 | He, Ran |
作者单位 | 1.Chinese Acad Sci, NLPR, CRIPAC, CEBSIT, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Sch Artif Intelligence, Beijing, Peoples R China 3.Baidu Inc, Dept Comp Vis Technol VIS, Beijing, Peoples R China 4.Tsinghua Univ, Dept Comp Sci & Technol, Beijing, Peoples R China |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Li, Zhihang,Xi, Teng,Zhang, Gang,et al. AutoDet: Pyramid Network Architecture Search for Object Detection[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2021(4):1087-1105. |
APA | Li, Zhihang,Xi, Teng,Zhang, Gang,Liu, Jingtuo,&He, Ran.(2021).AutoDet: Pyramid Network Architecture Search for Object Detection.INTERNATIONAL JOURNAL OF COMPUTER VISION(4),1087-1105. |
MLA | Li, Zhihang,et al."AutoDet: Pyramid Network Architecture Search for Object Detection".INTERNATIONAL JOURNAL OF COMPUTER VISION .4(2021):1087-1105. |
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 | ||
Li2021_Article_AutoD(2604KB) | 期刊论文 | 作者接受稿 | 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