Semi-Supervised Learning with Variational Bayesian Inference and Maximum Uncertainty Regularization
This work addresses the problem of improving semi-supervised learning performance for researchers and practitioners using consistency regularization methods, offering incremental improvements.
This paper introduces two methods to enhance semi-supervised learning: weight perturbation (WP) via variational Bayesian inference (VBI) and maximum uncertainty regularization (MUR). These methods improve classification errors in various consistency regularization-based approaches.
We propose two generic methods for improving semi-supervised learning (SSL). The first integrates weight perturbation (WP) into existing "consistency regularization" (CR) based methods. We implement WP by leveraging variational Bayesian inference (VBI). The second method proposes a novel consistency loss called "maximum uncertainty regularization" (MUR). While most consistency losses act on perturbations in the vicinity of each data point, MUR actively searches for "virtual" points situated beyond this region that cause the most uncertain class predictions. This allows MUR to impose smoothness on a wider area in the input-output manifold. Our experiments show clear improvements in classification errors of various CR based methods when they are combined with VBI or MUR or both.