Self-supervised Representation Learning with Relative Predictive Coding
From MaRDI portal
Publication:6363341
arXiv2103.11275MaRDI QIDQ6363341
Author name not available (Why is that?)
Publication date: 20 March 2021
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.
Has companion code repository: https://github.com/martinmamql/relative_predictive_coding
This page was built for publication: Self-supervised Representation Learning with Relative Predictive Coding
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6363341)