MixBag: Bag-Level Data Augmentation for Learning from Label Proportions
This addresses the weakly supervised learning challenge of training instance-level classifiers without instance labels, but it is incremental as it builds on existing LLP methods.
The paper tackles the problem of learning from label proportions (LLP) by proposing MixBag, a bag-level data augmentation method, and a confidence interval loss, which improve instance-level classification accuracy as shown in experiments.
Learning from label proportions (LLP) is a promising weakly supervised learning problem. In LLP, a set of instances (bag) has label proportions, but no instance-level labels are given. LLP aims to train an instance-level classifier by using the label proportions of the bag. In this paper, we propose a bag-level data augmentation method for LLP called MixBag, based on the key observation from our preliminary experiments; that the instance-level classification accuracy improves as the number of labeled bags increases even though the total number of instances is fixed. We also propose a confidence interval loss designed based on statistical theory to use the augmented bags effectively. To the best of our knowledge, this is the first attempt to propose bag-level data augmentation for LLP. The advantage of MixBag is that it can be applied to instance-level data augmentation techniques and any LLP method that uses the proportion loss. Experimental results demonstrate this advantage and the effectiveness of our method.