Detecting data points deviating from the training distribution is pivotal for
ensuring reliable machine learning. Extensive research has been dedicated to
the challenge, spanning classical anomaly detection techniques to contemporary
out-of-distribution (OOD) detection approaches. Whil
使用无标签数据来规范机器学习模型已经显示出改善检测超出分布数据的安全性和可靠性的潜力。一个新的学习框架 SAL(分割与学习)通过从无标签数据中分离候选离群值然后使用这些候选离群值和标记的正态数据训练离群值分类器,理论上证明了 SAL 能以较小的错误率分离候选离群值,这为学习到的离群值分类器提供了泛化保证。实证结果表明 SAL 在常见基准测试上取得了最先进的性能。