MixBag: Bag-Level Data Augmentation for Learning from Label Proportions
-
- Takanori Asanomi
- Kyushu University,Fukuoka,Japan
-
- Shinnosuke Matsuo
- Kyushu University,Fukuoka,Japan
-
- Daiki Suehiro
- Kyushu University,Fukuoka,Japan
-
- Ryoma Bise
- Kyushu University,Fukuoka,Japan
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
-
- 2023 IEEE/CVF International Conference on Computer Vision (ICCV)
-
2023 IEEE/CVF International Conference on Computer Vision (ICCV) 16524-16533, 2023-10-01
IEEE
- Tweet
キーワード
詳細情報 詳細情報について
-
- CRID
- 1360021390582777344
-
- 資料種別
- journal article
-
- データソース種別
-
- Crossref
- KAKEN
- OpenAIRE
