Pseudo Labels Regularization for Imbalanced Partial-Label Learning
This addresses label imbalance in weakly supervised learning, which is an incremental improvement for partial-label learning methods.
The paper tackles the problem of imbalanced partial-label learning, where tail classes are hard to learn due to small total weight, and proposes a pseudo-label regularization technique that achieves state-of-the-art results on standardized benchmarks.
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.