新研究推动AI系统的分布外检测能力

报道来源 [4]

1. arXiv cs.LG TIER_1 English(EN) · Fengqiang Wan, Qing-Yuan Jiang, Yang Yang · 2026-05-28 04:00

   AOE：通过重新校准异常值标签实现详尽的分布外检测

   arXiv:2605.28021v1 Announce Type: new Abstract: Out-of-distribution (OOD) detection is essential for deploying machine learning models in open-world and safety-critical scenarios, where test inputs may deviate from the training distribution and overconfident predictions on unknow…

2. arXiv cs.AI TIER_1 English(EN) · Bo Peng, Yadan Luo, Yonggang Zhang, Yixuan Li, Zhen Fang · 2026-05-25 04:00

   ConjNorm：可处理的分布外检测密度估计

   arXiv:2402.17888v5 Announce Type: replace-cross Abstract: Post-hoc out-of-distribution (OOD) detection has garnered intensive attention in reliable machine learning. Many efforts have been dedicated to deriving score functions based on logits, distances, or rigorous data distribu…

3. arXiv cs.AI TIER_1 English(EN) · Jihyeon Baek, Seunghoon Lee, Gitaek Kwon, Doohyun Park · 2026-05-22 04:00

   机器学习与深度学习在分布外检测中的比较研究

   arXiv:2605.10181v2 Announce Type: replace-cross Abstract: Out-of-distribution (OOD) detection is essential for building reliable AI systems, as models that produce outputs for invalid inputs cannot be trusted. Although deep learning (DL) is often assumed to outperform traditional…

4. arXiv stat.ML TIER_1 English(EN) · Randolph W. Linderman (Electrical and Computer Engineering Department, Duke University, Durham, NC, USA), Noah Cowan (Statistics Department, Stanford University, Stanford, CA, USA), Yiran Chen (Electrical and Computer Engineering Department, Duke Univers… · 2026-05-28 04:00

   从贝叶斯非参数视角看马氏距离在分布外检测中的应用

   arXiv:2502.08695v2 Announce Type: replace Abstract: Bayesian nonparametric methods are naturally suited to the problem of out-of-distribution (OOD) detection. However, these techniques have largely been eschewed in favor of simpler methods based on distances between pre-trained o…