GAIA-Universe: Everything is Super-Netify

doi:10.1109/TPAMI.2023.3276392

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	GAIA-Universe: Everything is Super-Netify
	Peng, Junran 2,4,5; Chang, Qing 4,5; Yin, Haoran 4,5; Bu, Xingyuan 1; Sun, Jiajun 4,5; Xie, Lingxi 2; Zhang, Xiaopeng 2; Tian, Qi 2; Zhang, Zhaoxiang 3,4,5
刊名	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
	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
DOI	10.1109/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
出版者	IEEE COMPUTER SOC
WOS记录号	WOS:001068816800023
资助机构	Major Project for New Generation of AI ; National Natural Science Foundation of China ; InnoHK program
内容类型	期刊论文
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.Beijing Inst Technol, Beijing 100190, Peoples R China 2.Huawei Technol Inc, Beijing 100190, Peoples R China 3.Ctr Excellence Brain Sci & Intelligence Technol CE, Ctr Artificial Intelligence & Robot, HKISICAS, Beijing 100190, Peoples R China 4.Univ Chinese Acad Sci UCAS, Beijing 100190, Peoples R China 5.Chinese Acad Sci CASIA, Ctr Res Intelligent Percept & Comp CRIPAC, Inst Automat, Natl Lab Pattern Recognit NLPR, Beijing 100045, 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.