EventMix: An efficient data augmentation strategy for event-based learning | |
Shen, Guobin2,3; Zhao, Dongcheng2; Zeng, Yi1,2,3,4 | |
刊名 | INFORMATION SCIENCES |
2023-10-01 | |
卷号 | 644页码:11 |
关键词 | Event based data augmentation Neuromorphic data Spiking neural networks Reasonable label assignment Gaussian mixture model |
ISSN号 | 0020-0255 |
DOI | 10.1016/j.ins.2023.119170 |
通讯作者 | Zeng, Yi(yi.zeng@ia.ac.cn) |
英文摘要 | High-quality and challenging event stream datasets play an important role in the design of an efficient event-driven mechanism that mimics the brain. Although event cameras can provide high dynamic range and low-energy event stream data, the scale is smaller and more difficult to obtain than traditional frame-based data, which restricts the development of neuromorphic computing. Data augmentation can improve the quantity and quality of the original data by processing more representations from the original data. This paper proposes an efficient data augmentation strategy for event stream data: EventMix. We carefully design the mixing of different event streams by Gaussian Mixture Model (GMM) to generate random 3D masks and achieve arbitrary shape mixing of event streams in the spatio-temporal dimension. By computing the relative distances of event streams, we propose a more reasonable way to assign labels to the mixed samples. The experimental results on multiple neuromorphic datasets have shown that our strategy can improve performance on neuromorphic classification tasks as well as neuromorphic human action recognition tasks both for ANNs and SNNs, and we have achieved state-of-the-art performance on DVS-CIFAR10, N-Caltech101, and DVS-Gesture datasets. |
资助项目 | National Key Research and Development Program[2020AAA0104305] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDB32070100] |
WOS关键词 | SPIKING ; DEEPER |
WOS研究方向 | Computer Science |
语种 | 英语 |
出版者 | ELSEVIER SCIENCE INC |
WOS记录号 | WOS:001026696600001 |
资助机构 | National Key Research and Development Program ; Strategic Priority Research Program of the Chinese Academy of Sciences |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/53684] |
专题 | 多模态人工智能系统全国重点实验室 |
通讯作者 | Zeng, Yi |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, Brain Inspired Cognit Intelligence Lab, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Sch Future Technol, Beijing, Peoples R China 4.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai, Peoples R China |
推荐引用方式 GB/T 7714 | Shen, Guobin,Zhao, Dongcheng,Zeng, Yi. EventMix: An efficient data augmentation strategy for event-based learning[J]. INFORMATION SCIENCES,2023,644:11. |
APA | Shen, Guobin,Zhao, Dongcheng,&Zeng, Yi.(2023).EventMix: An efficient data augmentation strategy for event-based learning.INFORMATION SCIENCES,644,11. |
MLA | Shen, Guobin,et al."EventMix: An efficient data augmentation strategy for event-based learning".INFORMATION SCIENCES 644(2023):11. |
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