Synthesizing Minority Samples for Long-Tailed Classification via Distribution Matching

Abstract

In many real-world applications, deep neural networks (DNNs) often perform poorly on datasets with long-tailed distributions. To address this issue, a promising approach is to propose an optimization objective to transform real majority samples into synthetic minority samples. However, this objective is designed only from the classification perspective. To this end, we propose a novel framework that synthesizes minority samples from the majority by considering both classification and distribution matching. Specifically, our method adjusts the distribution of synthetic minority samples to closely align with that of the true minority class, while enforcing the synthetic samples to learn more generalizable and discriminative features of the minority class. Experimental results on several standard benchmark datasets demonstrate the effectiveness of our method in both long-tailed classification and synthesizing high-quality synthetic minority samples.