Self-supervised Representation Learning with Relative Predictive Coding
arXiv:2103.11275
Abstract
This paper introduces Relative Predictive Coding (RPC), a new contrastive representation learning objective that maintains a good balance among training stability, minibatch size sensitivity, and downstream task performance. The key to the success of RPC is two-fold. First, RPC introduces the relative parameters to regularize the objective for boundedness and low variance. Second, RPC contains no logarithm and exponential score functions, which are the main cause of training instability in prior contrastive objectives. We empirically verify the effectiveness of RPC on benchmark vision and speech self-supervised learning tasks. Lastly, we relate RPC with mutual information (MI) estimation, showing RPC can be used to estimate MI with low variance.
References in corpus (12)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- A Simple Framework for Contrastive Learning of Visual Representations
- Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
- Estimating divergence functionals and the likelihood ratio by convex risk minimization
- Contrastive Multiview Coding
- Large Batch Training of Convolutional Networks
- Big Self-Supervised Models are Strong Semi-Supervised Learners
- On Mutual Information Maximization for Representation Learning
- A Mutual Information Maximization Perspective of Language Representation Learning
- A family of statistical symmetric divergences based on Jensen's inequality
- Relative Density-Ratio Estimation for Robust Distribution Comparison
- Neural Methods for Point-wise Dependency Estimation