GAIA-Universe: Everything is Super-Netify | |
Peng, Junran2,4,5; Chang, Qing4,5; Yin, Haoran4,5; Bu, Xingyuan1; Sun, Jiajun4,5; Xie, Lingxi2; Zhang, Xiaopeng2; Tian, Qi2; Zhang, Zhaoxiang3,4,5 | |
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. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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