Jaehyung Kim, Jongheon Jeong, Jinwoo Shin
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.
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Image Classification | CIFAR-10-LT (ρ=10) | Error Rate | 12.5 | M2m |
| Few-Shot Image Classification | CIFAR-10-LT (ρ=10) | Error Rate | 12.5 | M2m |
| Generalized Few-Shot Classification | CIFAR-10-LT (ρ=10) | Error Rate | 12.5 | M2m |
| Long-tail Learning | CIFAR-10-LT (ρ=10) | Error Rate | 12.5 | M2m |
| Generalized Few-Shot Learning | CIFAR-10-LT (ρ=10) | Error Rate | 12.5 | M2m |