Pseudo Labels Regularization for Imbalanced Partial-Label Learning

TL;DR

This paper introduces a pseudo-label regularization method for imbalanced partial-label learning, effectively addressing class imbalance issues and improving performance on standard benchmarks.

Contribution

It proposes a novel regularization technique that penalizes head class pseudo labels, enhancing learning for tail classes in imbalanced PLL scenarios.

Findings

Achieves state-of-the-art results on benchmark datasets.

Effectively mitigates class imbalance in PLL.

Improves tail class learning despite label distribution challenges.

Abstract

Partial-label learning (PLL) is an important branch of weakly supervised learning where the single ground truth resides in a set of candidate labels, while the research rarely considers the label imbalance. A recent study for imbalanced partial-Label learning proposed that the combinatorial challenge of partial-label learning and long-tail learning lies in matching between a decent marginal prior distribution with drawing the pseudo labels. However, we believe that even if the pseudo label matches the prior distribution, the tail classes will still be difficult to learn because the total weight is too small. Therefore, we propose a pseudo-label regularization technique specially designed for PLL. By punishing the pseudo labels of head classes, our method implements state-of-art under the standardized benchmarks compared to the previous PLL methods.