SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learning

TL;DR

SoftMatch introduces a novel semi-supervised learning method that balances the quantity and quality of pseudo-labels, improving model performance across diverse tasks by using a confidence-based weighting scheme.

Contribution

The paper proposes SoftMatch, a new approach that overcomes the pseudo-labeling trade-off by maintaining high quantity and quality of pseudo-labels through a confidence-weighted scheme.

Findings

SoftMatch significantly improves performance on image, text, and imbalanced classification benchmarks.

The confidence-based weighting scheme effectively balances pseudo-label quantity and quality.

SoftMatch outperforms existing semi-supervised learning methods across various datasets.

Abstract

The critical challenge of Semi-Supervised Learning (SSL) is how to effectively leverage the limited labeled data and massive unlabeled data to improve the model's generalization performance. In this paper, we first revisit the popular pseudo-labeling methods via a unified sample weighting formulation and demonstrate the inherent quantity-quality trade-off problem of pseudo-labeling with thresholding, which may prohibit learning. To this end, we propose SoftMatch to overcome the trade-off by maintaining both high quantity and high quality of pseudo-labels during training, effectively exploiting the unlabeled data. We derive a truncated Gaussian function to weight samples based on their confidence, which can be viewed as a soft version of the confidence threshold. We further enhance the utilization of weakly-learned classes by proposing a uniform alignment approach. In experiments, SoftMatch shows substantial improvements across a wide variety of benchmarks, including image, text, and imbalanced classification.