The deployment of machine learning solutions in real-world scenarios often involves addressing the challenge of out-of-distribution (OOD) detection. While significant efforts have been devoted to OOD detection in classical supervised settings, the context of weakly supervised learning, particularly the Multiple Instance Learning (MIL) framework, remains under-explored. In this study, we tackle this challenge by adapting post-hoc OOD detection methods to the MIL setting while introducing a novel benchmark specifically designed to assess OOD detection performance in weakly supervised scenarios. Extensive experiments based on diverse public datasets do not reveal a single method with a clear advantage over the others. Although DICE emerges as the best-performing method overall, it exhibits significant shortcomings on some datasets, emphasizing the complexity of this under-explored and challenging topic. Our findings shed light on the complex nature of OOD detection under the MIL framework, emphasizing the importance of developing novel, robust, and reliable methods that can generalize effectively in a weakly supervised context. The code for the paper is available here: https://github.com/loic-lb/OOD_MIL.

翻译：机器学习解决方案在实际场景中的部署常需应对分布外（OOD）检测的挑战。尽管传统监督学习中的OOD检测已有大量研究，但弱监督学习，特别是多实例学习（MIL）框架下的相关探索仍显不足。本研究通过将事后OOD检测方法适配至MIL框架来解决这一挑战，同时引入了一个专门用于评估弱监督场景下OOD检测性能的新型基准。基于多样公开数据集的广泛实验表明，未发现单一方法具有显著优势。尽管DICE整体表现最佳，但在部分数据集上仍存在明显缺陷，凸显了这一待探索且具有挑战性研究课题的复杂性。我们的发现揭示了MIL框架下OOD检测的复杂本质，强调了在弱监督环境下开发兼具泛化能力与鲁棒性的新型可靠方法的重要性。论文代码已开源：https://github.com/loic-lb/OOD_MIL