In this paper, we propose the Adversarial Denoising Diffusion Model (ADDM). The ADDM is based on the Denoising Diffusion Probabilistic Model (DDPM) but complementarily trained by adversarial learning. The proposed adversarial learning is achieved by classifying model-based denoised samples and samples to which random Gaussian noise is added to a specific sampling step. With the addition of explicit adversarial learning on data samples, ADDM can learn the semantic characteristics of the data more robustly during training, which achieves a similar data sampling performance with much fewer sampling steps than DDPM. We apply ADDM to anomaly detection in unsupervised MRI images. Experimental results show that the proposed ADDM outperformed existing generative model-based unsupervised anomaly detection methods. In particular, compared to other DDPM-based anomaly detection methods, the proposed ADDM shows better performance with the same number of sampling steps and similar performance with 50% fewer sampling steps.

翻译：本文提出对抗去噪扩散模型（Adversarial Denoising Diffusion Model, ADDM）。ADDM基于去噪扩散概率模型（Denoising Diffusion Probabilistic Model, DDPM），但通过对抗学习进行补充训练。所提出的对抗学习通过区分基于模型去噪后的样本与在特定采样步骤中添加随机高斯噪声的样本实现。由于在数据样本上引入了显式对抗学习，ADDM能够在训练过程中更鲁棒地学习数据的语义特征，从而以远少于DDPM的采样步数实现相似的数据采样性能。我们将ADDM应用于无监督MRI图像的异常检测。实验结果表明，所提出的ADDM优于现有基于生成模型的无监督异常检测方法。特别是，与其他基于DDPM的异常检测方法相比，所提出的ADDM在相同采样步数下展现了更优性能，且在采样步数减少50%时仍保持相似性能。