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

書誌事項

公開日
2023-10-01
資源種別
journal article
権利情報
  • https://doi.org/10.15223/policy-029
  • https://doi.org/10.15223/policy-037
DOI
  • 10.1109/iccv51070.2023.01519
  • 10.48550/arxiv.2308.08822
公開者
IEEE

説明

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.

Accepted at ICCV2023

収録刊行物

被引用文献 (2)*注記

もっと見る

参考文献 (33)*注記

もっと見る

関連プロジェクト

もっと見る

詳細情報 詳細情報について

問題の指摘

ページトップへ