Out-of-distribution (OOD) detection is a crucial task for ensuring the reliability and safety of deep learning. Currently, discriminator models outperform other methods in this regard. However, the feature extraction process used by discriminator models suffers from the loss of critical information, leaving room for bad cases and malicious attacks. In this paper, we introduce a new perceptron bias assumption that suggests discriminator models are more sensitive to certain features of the input, leading to the overconfidence problem. To address this issue, we propose a novel framework that combines discriminator and generation models and integrates diffusion models (DMs) into OOD detection. We demonstrate that the diffusion denoising process (DDP) of DMs serves as a novel form of asymmetric interpolation, which is well-suited to enhance the input and mitigate the overconfidence problem. The discriminator model features of OOD data exhibit sharp changes under DDP, and we utilize the norm of this change as the indicator score. Our experiments on CIFAR10, CIFAR100, and ImageNet show that our method outperforms SOTA approaches. Notably, for the challenging InD ImageNet and OOD species datasets, our method achieves an AUROC of 85.7, surpassing the previous SOTA method's score of 77.4. Our implementation is available at \url{https://github.com/luping-liu/DiffOOD}.

翻译：分布外（OOD）检测是确保深度学习可靠性和安全性的关键任务。目前，判别模型在此方面优于其他方法。然而，判别模型使用的特征提取过程会丢失关键信息，为不良案例和恶意攻击留下可乘之机。本文引入一种新的感知器偏差假设，认为判别模型对输入的某些特征更为敏感，从而导致过度自信问题。为解决这一问题，我们提出一种结合判别模型与生成模型的新框架，并将扩散模型（DMs）融入OOD检测。我们证明，扩散模型中的扩散去噪过程（DDP）作为一种新型非对称插值，非常适合用于增强输入并缓解过度自信问题。在DDP作用下，OOD数据的判别模型特征呈现剧烈变化，我们利用这种变化的范数作为指示分数。在CIFAR10、CIFAR100和ImageNet上的实验表明，我们的方法优于当前最先进（SOTA）方法。值得注意的是，对于具有挑战性的InD ImageNet和OOD物种数据集，我们的方法实现了85.7的AUROC，超越了此前SOTA方法77.4的得分。我们的实现代码已开源在\url{https://github.com/luping-liu/DiffOOD}。