Denoising Probabilistic Models (DPMs) represent an emerging domain of generative models that excel in generating diverse and high-quality images. However, most current training methods for DPMs often neglect the correlation between timesteps, limiting the model's performance in generating images effectively. Notably, we theoretically point out that this issue can be caused by the cumulative estimation gap between the predicted and the actual trajectory. To minimize that gap, we propose a novel \textit{sequence-aware} loss that aims to reduce the estimation gap to enhance the sampling quality. Furthermore, we theoretically show that our proposed loss function is a tighter upper bound of the estimation loss in comparison with the conventional loss in DPMs. Experimental results on several benchmark datasets including CIFAR10, CelebA, and CelebA-HQ consistently show a remarkable improvement of our proposed method regarding the image generalization quality measured by FID and Inception Score compared to several DPM baselines. Our code and pre-trained checkpoints are available at \url{https://github.com/VinAIResearch/SA-DPM}.

翻译：去噪概率模型（DPMs）代表了一个新兴的生成模型领域，在生成多样且高质量的图像方面表现卓越。然而，目前大多数DPMs的训练方法常忽略时间步之间的相关性，限制了模型有效生成图像的性能。值得注意的是，我们从理论上指出，该问题可能源于预测轨迹与实际轨迹之间的累积估计偏差。为最小化这一偏差，我们提出了一种新颖的序列感知损失函数，旨在通过减少估计偏差来提升采样质量。进一步地，我们从理论上证明，与DPMs中的传统损失函数相比，我们所提出的损失函数是估计损失更紧的上界。在包括CIFAR10、CelebA和CelebA-HQ在内的多个基准数据集上的实验结果表明，与若干DPM基线方法相比，我们提出的方法在通过FID和Inception Score衡量的图像泛化质量上取得了显著改进。我们的代码和预训练检查点已开源至\url{https://github.com/VinAIResearch/SA-DPM}。