arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.04297cs.CV
收藏

使用动量对比学习改进基线

Improved Baselines with Momentum Contrastive Learning

Facebook AI Research (FAIR)(Facebook人工智能研究院(FAIR))

Xinlei Chen, Haoqi Fan, Ross Girshick, Kaiming He

摘要:

对比无监督学习最近已经显示出令人鼓舞的进展,例如,动量对比(MoCo)和Simplified。在本说明中,我们通过在MoCo框架中实现Simplified的两个设计改进来验证它们的有效性。通过对MoCo的简单修改--即使用MLP投影头和更多的数据增强--我们建立了更强大的基线,性能优于Simplified,并且不需要大量的训练批次。我们希望这将使最先进的无监督学习研究更容易获得。代码将被公开。

英文摘要:

Contrastive unsupervised learning has recently shown encouraging progress, e.g., in Momentum Contrast (MoCo) and SimCLR. In this note, we verify the effectiveness of two of SimCLR's design improvements by implementing them in the MoCo framework. With simple modifications to MoCo---namely, using an MLP projection head and more data augmentation---we establish stronger baselines that outperform SimCLR and do not require large training batches. We hope this will make state-of-the-art unsupervised learning research more accessible. Code will be made public.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑