中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
GAIA-Universe: Everything is Super-Netify

文献类型：期刊论文

作者Peng, Junran1,2,3; Chang, Qing2,3; Yin, Haoran2,3; Bu, Xingyuan4; Sun, Jiajun2,3; Xie, Lingxi1; Zhang, Xiaopeng1; Tian, Qi1; Zhang, Zhaoxiang2,3,5
刊名IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
出版日期2023-10-01
卷号45期号:10页码:11856-11868
关键词Computer vision object detection semantic segmentation AutoML
ISSN号0162-8828
DOI10.1109/TPAMI.2023.3276392
通讯作者Zhang, Zhaoxiang(zhaoxiang.zhang@ia.ac.cn)
英文摘要Pre-training on large-scale datasets has played an increasingly significant role in computer vision and natural language processing recently. However, as there exist numerous application scenarios that have distinctive demands such as certain latency constraints and specialized data distributions, it is prohibitively expensive to take advantage of large-scale pre-training for per-task requirements. we focus on two fundamental perception tasks (object detection and semantic segmentation) and present a complete and flexible system named GAIA-Universe(GAIA), which could automatically and efficiently give birth to customized solutions according to heterogeneous downstream needs through data union and super-net training. GAIA is capable of providing powerful pre-trained weights and searching models that conform to downstream demands such as hardware constraints, computation constraints, specified data domains, and telling relevant data for practitioners who have very few datapoints on their tasks. With GAIA, we achieve promising results on COCO, Objects365, Open Images, BDD100 k, and UODB which is a collection of datasets including KITTI, VOC, WiderFace, DOTA, Clipart, Comic, and more. Taking COCO as an example, GAIA is able to efficiently produce models covering a wide range of latency from 16 ms to 53 ms, and yields AP from 38.2 to 46.5 without whistles and bells. GAIA is released at https://github.com/GAIA-vision.
资助项目Major Project for New Generation of AI ; National Natural Science Foundation of China[2018AAA0100400] ; National Natural Science Foundation of China[61836014] ; National Natural Science Foundation of China[U21B2042] ; National Natural Science Foundation of China[62072457] ; InnoHK program ; [62006231]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001068816800023
出版者IEEE COMPUTER SOC
资助机构Major Project for New Generation of AI ; National Natural Science Foundation of China ; InnoHK program
源URL[http://ir.ia.ac.cn/handle/173211/53035]  
专题多模态人工智能系统全国重点实验室
通讯作者Zhang, Zhaoxiang
作者单位1.Huawei Technol Inc, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci UCAS, Beijing 100190, Peoples R China
3.Chinese Acad Sci CASIA, Ctr Res Intelligent Percept & Comp CRIPAC, Inst Automat, Natl Lab Pattern Recognit NLPR, Beijing 100045, Peoples R China
4.Beijing Inst Technol, Beijing 100190, Peoples R China
5.Ctr Excellence Brain Sci & Intelligence Technol CE, Ctr Artificial Intelligence & Robot, HKISICAS, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Peng, Junran,Chang, Qing,Yin, Haoran,et al. GAIA-Universe: Everything is Super-Netify[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2023,45(10):11856-11868.
APA Peng, Junran.,Chang, Qing.,Yin, Haoran.,Bu, Xingyuan.,Sun, Jiajun.,...&Zhang, Zhaoxiang.(2023).GAIA-Universe: Everything is Super-Netify.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,45(10),11856-11868.
MLA Peng, Junran,et al."GAIA-Universe: Everything is Super-Netify".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 45.10(2023):11856-11868.

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。