MixBag: Bag-Level Data Augmentation for Learning from Label Proportions

2023/08/17 by Asanomi, Takanori, Matsuo, Shinnosuke, Suehiro, Daiki +1 · 2 citations
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2308.08822

Abstract

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.

Cited by

• Weakly-Supervised Domain Adaptation with Proportion-Constrained Pseudo-Labeling
• Towards Privacy-Preserving Fine-Grained Visual Classification via Hierarchical Learning from Label Proportions

Related

• Theoretical Proportion Label Perturbation for Learning from Label Proportions in Large Bags
• Learning from Label Proportion with Online Pseudo-Label Decision by Regret Minimization
• Forming Auxiliary High-confident Instance-level Loss to Promote Learning from Label Proportions
• Evaluating LLP Methods: Challenges and Approaches
• Learning from Label Proportions with Instance-wise Consistency