摘要
Recently, contrastive learning has shown its effectiveness in self-supervised learning by training features of augmentations of input images based on the contrastive loss. This paper aims to introduce contrastive learning and discuss the effects of augmentations, features, and parameters of contrastive learning. Interactive figures are developed to demonstrate the effective schemes proposed in contrastive learning and can be accessed on IEEE Xplore.
原文 | English |
---|---|
頁(從 - 到) | 79-80 |
頁數 | 2 |
期刊 | IEEE Computational Intelligence Magazine |
卷 | 19 |
發行號 | 1 |
DOIs | |
出版狀態 | Published - 1 2月 2024 |