Title: 《Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere》 Author:Tongzhou Wang ; Phillip Isola

文章指出了Contrastive representation learning的两个重要属性： Alignment: two samples forming a positive pair should be mapped to nearby features, and thus be (mostly) invariant to unneeded noise factors. Uniformity: feature vectors should be roughly uniformly distributed on the unit hypersphere, pre-serving as much information of the data as possible. 作者证明了现有的一些对比学习的算法正是较好地满足了这两条性质才取得了不错的效果。 作者提出了一个可优化的 metric 来直接量化这两条属性。通过直接优化该loss，也取得了较好的效果。

内容中包含的图片若涉及版权问题，请及时与我们联系删除