The paper proposes a novel problem in multi-class Multiple-Instance Learning (MIL) called Learning from the Majority Label (LML). In LML, the majority class of instances in a bag is assigned as the bag's label. LML aims to classify instances using bag-level majority classes. This problem is valuable in various applications. Existing MIL methods are unsuitable for LML due to aggregating confidences, which may lead to inconsistency between the bag-level label and the label obtained by counting the number of instances for each class. This may lead to incorrect instance-level classification. We propose a counting network trained to produce the bag-level majority labels estimated by counting the number of instances for each class. This led to the consistency of the majority class between the network outputs and one obtained by counting the number of instances. Experimental results show that our counting network outperforms conventional MIL methods on four datasets The code is publicly available at https://github.com/Shiku-Kaito/Counting-Network-for-Learning-from-Majority-Label.

翻译：本文提出了一种多类多实例学习（MIL）中的新问题，即基于多数标签学习（LML）。在LML中，包中实例的多数类别被赋予为该包的标签。LML旨在利用包级多数类别对实例进行分类。该问题在多种应用中具有重要价值。现有MIL方法由于采用置信度聚合策略，可能导致包级标签与通过统计各类别实例数量所得标签不一致，从而不适用于LML。这可能导致错误的实例级分类。我们提出了一种计数网络，通过统计各类别实例数量来估计包级多数标签。这使得网络输出的多数类别与统计实例数量所得的多数类别保持一致。实验结果表明，在四个数据集上，我们的计数网络优于传统MIL方法。代码已在https://github.com/Shiku-Kaito/Counting-Network-for-Learning-from-Majority-Label 公开。