-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Asanomi_2023_ICCV, author = {Asanomi, Takanori and Matsuo, Shinnosuke and Suehiro, Daiki and Bise, Ryoma}, title = {MixBag: Bag-Level Data Augmentation for Learning from Label Proportions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {16570-16579} }
MixBag: Bag-Level Data Augmentation for Learning from Label Proportions
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.
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, which is 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 in order 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.
Related Material