Zhongyi Fan

Multi-Step Denoising Scheduled Sampling: Towards Alleviating Exposure Bias for Diffusion Models

Denoising Diffusion Probabilistic Models (DDPMs) have achieved significant success in generation tasks. Nevertheless, the exposure bias issue, i.e., the natural discrepancy between the training (the output of each step is calculated individually by a given input) and inference (the output of each st…