M2m: Imbalanced Classification via Major-to-minor Translation
This addresses the problem of poor generalization in deep neural networks for imbalanced datasets, which is common in real-world scenarios, and represents an incremental improvement over existing methods.
The paper tackles class imbalance in training datasets by augmenting minority classes through translating samples from majority classes, improving generalization on minority classes and surpassing previous state-of-the-art methods in imbalanced classification.
In most real-world scenarios, labeled training datasets are highly class-imbalanced, where deep neural networks suffer from generalizing to a balanced testing criterion. In this paper, we explore a novel yet simple way to alleviate this issue by augmenting less-frequent classes via translating samples (e.g., images) from more-frequent classes. This simple approach enables a classifier to learn more generalizable features of minority classes, by transferring and leveraging the diversity of the majority information. Our experimental results on a variety of class-imbalanced datasets show that the proposed method improves the generalization on minority classes significantly compared to other existing re-sampling or re-weighting methods. The performance of our method even surpasses those of previous state-of-the-art methods for the imbalanced classification.