Training Unbiased Diffusion Models From Biased Dataset

arXiv:2403.01189v1 Announce Type: new
Abstract: With significant advancements in diffusion models, addressing the potential risks of dataset bias becomes increasingly important. Since generated outputs directly suffer from dataset bias, mitigating latent bias becomes a key factor in improving sample quality and proportion. This paper proposes time-dependent importance reweighting to mitigate the bias for the diffusion models. We demonstrate that the time-dependent density ratio becomes more precise than previous approaches, thereby minimizing error propagation in generative learning. While directly applying it …

arxiv cs.cv cs.lg dataset diffusion diffusion models training type unbiased