arXiv:2501.08005cs.CVcs.AI2025-01ICCV被引 1

利用对抗样本的批量统计特性,提升对细微数据分布偏移的检测能力。

DisCoPatch: Taming Adversarially-driven Batch Statistics for Improved Out-of-Distribution Detection

  • 通过变分自编码器的次优输出生成对抗样本,增强判别器边界区分能力。
  • 在ImageNet-1K(-C)上达95.5% AUROC,Near-OOD任务上达95.0% AUROC。
  • 模型仅25MB,推理延迟低,适合实际部署场景。

分布外(OOD)检测在诸多应用中具有重要意义。尽管语义和领域偏移型OOD问题已得到充分研究,本文聚焦于协变量偏移——数据分布中的细微变化,这类变化可能降低机器学习性能。我们假设,检测此类细微偏移有助于更清晰理解分布内边界,从而提升OOD检测效果。在使用批归一化(BN)训练的对抗判别器中,真实样本与对抗样本形成具有独特批量统计特性的不同域,这一特性被用于OOD检测。本文提出DisCoPatch,一种无监督对抗变分自编码器(VAE)框架,利用该机制。推理时,批次由同一图像的块组成,确保数据分布一致,使模型可依赖批量统计。DisCoPatch以VAE的次优输出(生成与重建结果)作为负样本训练判别器,从而强化其对分布内样本与协变量偏移之间边界的划分能力。通过紧化边界,DisCoPatch在公开的OOD检测基准上达到顶尖水平。该模型不仅在检测协变量偏移上表现优异,在ImageNet-1K(-C)上实现95.5% AUROC,且在所有公开的Near-OOD基准上均超越先前方法(95.0% AUROC)。模型大小仅25MB,推理延迟显著低于现有方法,具备高效实用优势。代码已公开。

原文摘要 · Abstract (English)

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.

OOD检测对抗学习批量归一化轻量级模型

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。