Abstract | ||
---|---|---|
This paper presents Prototypical Contrastive Learning (PCL), an unsupervised representation learning method that addresses the fundamental limitations of the popular instance-wise contrastive learning. PCL implicitly encodes semantic structures of the data into the learned embedding space, and prevents the network from solely relying on low-level cues for solving unsupervised learning tasks. Specifically, we introduce prototypes as latent variables to help find the maximum-likelihood estimation of the network parameters in an Expectation-Maximization framework. We iteratively perform E-step as finding the distribution of prototypes via clustering and M-step as optimizing the network via contrastive learning. We propose ProtoNCE loss, a generalized version of the InfoNCE loss for contrastive learning by encouraging representations to be closer to their assigned prototypes. PCL achieves state-of-the-art results on multiple unsupervised representation learning benchmarks, with >10% accuracy improvement in low-resource transfer tasks. |
Year | Venue | DocType |
---|---|---|
2021 | ICLR | Conference |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Junnan Li | 1 | 58 | 10.46 |
Zhou, P. | 2 | 88 | 11.59 |
Caiming Xiong | 3 | 969 | 69.56 |
Richard Socher | 4 | 6770 | 230.61 |
Steven C. H. Hoi | 5 | 3830 | 174.61 |