用无标签数据中的梯度中位数，自动发现异常样本并提升检测效果。
Medix: Out-of-Distribution Detection from Unlabeled Wild Data via Robust Gradient Statistics
- 基于梯度中位数统计，从无标签野数据中识别潜在异常点。
- 在开放世界设置下，各项指标均优于现有方法，误差率更低。
- 适合需要高鲁棒性的实际部署场景，尤其适用于无标注数据环境。
分布外（OOD）检测对于保障机器学习系统在真实应用中的鲁棒性至关重要。近期方法尝试利用无标签数据，展现出增强OOD检测能力的潜力。然而，由于无标签野数据中混合了分布内（InD）和分布外样本，有效利用这些数据仍具挑战性。缺乏明确的分布外样本使训练最优的OOD分类器变得复杂。本文提出Medix，一种新框架，通过中位数为基础的鲁棒梯度统计，从无标签数据中识别潜在异常点。使用中位数是因为其对噪声和异常值具有强鲁棒性，能稳定估计中心趋势。利用这些识别出的异常点与有标签的InD数据，训练出更鲁棒的OOD分类器。理论分析表明，Medix具有较低的误差界。实验结果进一步验证了该方法的有效性，在开放世界设置下全面超越现有方法。
原文摘要 · Abstract (English)
Out-of-distribution (OOD) detection plays a crucial role in ensuring the robustness of machine learning systems deployed in real-world applications. Recent approaches have explored the use of unlabeled data, showing potential for enhancing OOD detection capabilities. However, effectively utilizing unlabeled in-the-wild data remains challenging due to the mixed nature of both in-distribution (InD) and OOD samples. The lack of a distinct set of OOD samples complicates the task of training an optimal OOD classifier. In this work, we introduce Medix, a novel framework designed to identify potential outliers from unlabeled data using the median-based robust gradient statistics. We use the median because it provides a stable estimate of the central tendency, as an OOD detection mechanism, due to its robustness against noise and outliers. Using these identified outliers, along with labeled InD data, we train a robust OOD classifier. From a theoretical perspective, we derive error bounds that demonstrate Medix achieves a low error rate. Empirical results further substantiate our claims, as Medix outperforms existing methods across the board in open-world settings.
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。