SimpleDet: A Simple and Versatile Distributed Framework for Object Detection and Instance Recognition
文献类型:期刊论文
作者 | Chen, Yuntao1![]() ![]() |
刊名 | JOURNAL OF MACHINE LEARNING RESEARCH
![]() |
出版日期 | 2019 |
卷号 | 20页码:8 |
关键词 | Object Detection Instance Recognition Distributed Training Mixed Precision Training |
ISSN号 | 1532-4435 |
通讯作者 | Chen, Yuntao(CHENYUNTAO2016@IA.AC.CN) |
英文摘要 | Object detection and instance recognition play a central role in many AI applications like autonomous driving, video surveillance and medical image analysis. However, training object detection models on large scale datasets remains computationally expensive and time consuming. This paper presents an efficient and open source object detection framework called SimpleDet which enables the training of state-of-the-art detection models on consumer grade hardware at large scale. SimpleDet covers a wide range of models including both high-performance and high-speed ones. SimpleDet is well-optimized for both low precision training and distributed training and achieves 70% higher throughput for the Mask R-CNN detector compared with existing frameworks. |
WOS研究方向 | Automation & Control Systems ; Computer Science |
语种 | 英语 |
WOS记录号 | WOS:000491132200020 |
出版者 | MICROTOME PUBL |
源URL | [http://ir.ia.ac.cn/handle/173211/26432] ![]() |
专题 | 自动化研究所_智能感知与计算研究中心 |
通讯作者 | Chen, Yuntao |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 2.TuSimple, Beijing, Peoples R China |
推荐引用方式 GB/T 7714 | Chen, Yuntao,Han, Chenxia,Li, Yanghao,et al. SimpleDet: A Simple and Versatile Distributed Framework for Object Detection and Instance Recognition[J]. JOURNAL OF MACHINE LEARNING RESEARCH,2019,20:8. |
APA | Chen, Yuntao.,Han, Chenxia.,Li, Yanghao.,Huang, Zehao.,Jiang, Yi.,...&Zhang, Zhaoxiang.(2019).SimpleDet: A Simple and Versatile Distributed Framework for Object Detection and Instance Recognition.JOURNAL OF MACHINE LEARNING RESEARCH,20,8. |
MLA | Chen, Yuntao,et al."SimpleDet: A Simple and Versatile Distributed Framework for Object Detection and Instance Recognition".JOURNAL OF MACHINE LEARNING RESEARCH 20(2019):8. |
入库方式: OAI收割
来源:自动化研究所
浏览0
下载0
收藏0
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。