Knowledge Commons of Institute of Automation,CAS
Contrastive Learning via Local Activity | |
Zhu H(祝贺)![]() ![]() ![]() ![]() | |
发表期刊 | Electronics
![]() |
2023-01 | |
页码 | 147 |
文章类型 | 研究论文 |
摘要 | Contrastive learning (CL) helps deep networks discriminate between positive and negative pairs in learning. As a powerful unsupervised pretraining method, CL has greatly reduced the performance gap with supervised training. However, current CL approaches mainly rely on sophisticated augmentations, a large number of negative pairs and chained gradient calculations, which are complex to use. To address these issues, in this paper, we propose the local activity contrast (LAC) algorithm, which is an unsupervised method based on two forward passes and locally defined loss to learn meaningful representations. The learning target of each layer is to minimize the activation value difference between two forward passes, effectively overcoming the limitations of applying CL above mentioned. We demonstrated that LAC could be a very useful pretraining method using reconstruction as the pretext task. Moreover, through pretraining with LAC, the networks exhibited competitive performance in various downstream tasks compared with other unsupervised learning methods. |
语种 | 英语 |
七大方向——子方向分类 | 类脑模型与计算 |
国重实验室规划方向分类 | 认知机理与类脑学习 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/51602 |
专题 | 脑图谱与类脑智能实验室_脑网络组研究 脑图谱与类脑智能实验室 |
通讯作者 | Zhu H(祝贺); Chen Y(陈阳) |
推荐引用方式 GB/T 7714 | Zhu H,Chen Y,Hu GY,et al. Contrastive Learning via Local Activity[J]. Electronics,2023:147. |
APA | Zhu H,Chen Y,Hu GY,&Yu S.(2023).Contrastive Learning via Local Activity.Electronics,147. |
MLA | Zhu H,et al."Contrastive Learning via Local Activity".Electronics (2023):147. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
2023_Zhu et al.pdf(1008KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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