Class-Balancing Diffusion Models
This addresses the issue of diffusion models failing on long-tailed data distributions, which are common in practice, by improving generation for underrepresented classes.
The paper tackles the problem of diffusion models performing poorly on class-imbalanced data, showing significant degradation in diversity and fidelity, especially for tail classes. The proposed Class-Balancing Diffusion Models (CBDM) with a distribution adjustment regularizer improves diversity and quality, as demonstrated on CIFAR100/CIFAR100LT datasets with outstanding downstream recognition performance.
Diffusion-based models have shown the merits of generating high-quality visual data while preserving better diversity in recent studies. However, such observation is only justified with curated data distribution, where the data samples are nicely pre-processed to be uniformly distributed in terms of their labels. In practice, a long-tailed data distribution appears more common and how diffusion models perform on such class-imbalanced data remains unknown. In this work, we first investigate this problem and observe significant degradation in both diversity and fidelity when the diffusion model is trained on datasets with class-imbalanced distributions. Especially in tail classes, the generations largely lose diversity and we observe severe mode-collapse issues. To tackle this problem, we set from the hypothesis that the data distribution is not class-balanced, and propose Class-Balancing Diffusion Models (CBDM) that are trained with a distribution adjustment regularizer as a solution. Experiments show that images generated by CBDM exhibit higher diversity and quality in both quantitative and qualitative ways. Our method benchmarked the generation results on CIFAR100/CIFAR100LT dataset and shows outstanding performance on the downstream recognition task.