Diffusion Denoising Process for Perceptron Bias in Out-of-distribution Detection

TL;DR

This paper introduces a diffusion denoising process integrated with discriminator models to improve out-of-distribution detection, addressing overconfidence issues and outperforming state-of-the-art methods on multiple datasets.

Contribution

It proposes a novel framework combining discriminator and diffusion models, utilizing diffusion denoising as asymmetric interpolation to enhance OOD detection accuracy.

Findings

Outperforms SOTA on CIFAR10, CIFAR100, ImageNet

Achieves 85.7 AUROC on challenging datasets

Utilizes diffusion denoising to detect feature sharp changes

Abstract

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}.