MixBag: Bag-Level Data Augmentation for Learning from Label Proportions
Authors:
- 1 October 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 16524-16533
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.Keywords
All Related Versions
Funding Information
- ACT-X
This publication has 19 references indexed in Scilit:
- MedMNIST v2 - A large-scale lightweight benchmark for 2D and 3D biomedical image classificationScientific Data, 2023
- ReMix: A General and Efficient Framework for Multiple Instance Learning Based Whole Slide Image Classification2022
- A novel multiple instance learning framework for COVID-19 severity assessment via data augmentation and self-supervised learningMedical Image Analysis, 2021
- Negative Pseudo Labeling Using Class Proportion for Semantic Segmentation in Pathology2020
- Randaugment: Practical automated data augmentation with a reduced search space2020
- AutoAugment: Learning Augmentation Strategies From Data2019
- Empirical Risk Minimization2017
- Deep Residual Learning for Image Recognition2016
- ImageNet: A large-scale hierarchical image database2009
- Principal component analysisChemometrics and Intelligent Laboratory Systems, 1987