DisCoPatch: 通过对抗驱动的批量统计来改进分布外检测
DisCoPatch: Taming Adversarially-driven Batch Statistics for Improved Out-of-Distribution Detection
AI总结：
DisCoPatch通过利用对抗驱动的批量统计改进分布外检测，实现高效且准确的检测性能。
摘要：
分布外（OOD）检测在许多应用中具有重要意义。尽管语义和领域转移的OOD问题已被广泛研究，本文聚焦于协变量转移——数据分布中的细微变化，这些变化可能会降低机器学习性能。我们假设检测这些细微变化可以加深对分布内边界的理解，最终提高OOD检测性能。在使用批量归一化（BN）训练的对抗判别器中，真实样本和对抗样本形成具有独特批量统计的独立领域——这一特性我们用于OOD检测。我们引入了DisCoPatch，一种无监督的对抗变分自编码器（VAE）框架，利用这一机制。在推理过程中，批次由同一张图像的补丁组成，确保数据分布的一致性，使模型能够依赖批量统计。DisCoPatch使用VAE的次优输出（生成和重建）作为负样本来训练判别器，从而提高其区分分布内样本和协变量转移的能力。通过收紧这一边界，DisCoPatch在公开的OOD检测基准中取得了最先进的结果。所提出的模型不仅在检测协变量转移方面表现出色，达到ImageNet-1K(-C)的95.5% AUROC，而且在公开的近分布外（Near-OOD）基准中也优于所有先前方法（95.0%）。凭借25MB的紧凑模型大小，它在显著较低的延迟下实现了高OOD检测性能，使其成为实际应用中高效且实用的解决方案。代码已公开。
英文摘要：
Out-of-distribution (OOD) detection holds significant importance across many applications. While semantic and domain-shift OOD problems are well-studied, this work focuses on covariate shifts - subtle variations in the data distribution that can degrade machine learning performance. We hypothesize that detecting these subtle shifts can improve our understanding of in-distribution boundaries, ultimately improving OOD detection. In adversarial discriminators trained with Batch Normalization (BN), real and adversarial samples form distinct domains with unique batch statistics - a property we exploit for OOD detection. We introduce DisCoPatch, an unsupervised Adversarial Variational Autoencoder (VAE) framework that harnesses this mechanism. During inference, batches consist of patches from the same image, ensuring a consistent data distribution that allows the model to rely on batch statistics. DisCoPatch uses the VAE's suboptimal outputs (generated and reconstructed) as negative samples to train the discriminator, thereby improving its ability to delineate the boundary between in-distribution samples and covariate shifts. By tightening this boundary, DisCoPatch achieves state-of-the-art results in public OOD detection benchmarks. The proposed model not only excels in detecting covariate shifts, achieving 95.5% AUROC on ImageNet-1K(-C) but also outperforms all prior methods on public Near-OOD (95.0%) benchmarks. With a compact model size of 25MB, it achieves high OOD detection performance at notably lower latency than existing methods, making it an efficient and practical solution for real-world OOD detection applications. The code is publicly available.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
