mlsanityData to 14 Oct 2026

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

arXiv 2308.08822 ↗First posted 17 Aug 2023cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 25 of its 37 references that are in the map. First posted on arXiv 17 Aug 2023.

Builds on

25 of 37 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  4. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  5. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  6. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  7. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
  8. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 901
  9. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  10. 2021MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classificationcited by 690
  11. 2017The Effectiveness of Data Augmentation in Image Classification using Deep Learningcited by 370
  12. 2019Fast AutoAugmentcited by 243
13 more
  1. 2020GridMask Data Augmentationcited by 123
  2. 2018Data Augmentation by Pairing Samples for Images Classificationcited by 96
  3. 2019Learning from Label Proportions with Consistency Regularizationcited by 34
  4. 2019Deep multi-class learning from label proportionscited by 33
  5. 2022ReMix: A General and Efficient Framework for Multiple Instance Learning based Whole Slide Image Classificationcited by 30
  6. 2017Co-training for Demographic Classification Using Deep Learning from Label Proportionscited by 28
  7. 2019Learning from Label Proportions with Generative Adversarial Networkscited by 25
  8. 2021A novel multiple instance learning framework for COVID-19 severity assessment via data augmentation and self-supervised learningcited by 19
  9. 2021Two-stage Training for Learning from Label Proportionscited by 19
  10. 2020Negative Pseudo Labeling using Class Proportion for Semantic Segmentation in Pathologycited by 12
  11. 2019Unified Generative Adversarial Networks for Controllable Image-to-Image Translationcited by 11
  12. 2020FenceMask: A Data Augmentation Approach for Pre-extracted Image Featurescited by 10
  13. 2023Learning from Label Proportion with Online Pseudo-Label Decision by Regret Minimizationcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 4; 2025: 2; 2026: 1.

8 papers.

  1. 2023Rethinking Multiple Instance Learning for Whole Slide Image Classification: A Bag-Level Classifier is a Good Instance-Level Teachercited by 9
  2. 2024Learning from Partial Label Proportions for Whole Slide Image Segmentationcited by 6
  3. 2024Theoretical Proportion Label Perturbation for Learning from Label Proportions in Large Bagscited by 2
  4. 2024Forming Auxiliary High-confident Instance-level Loss to Promote Learning from Label Proportionscited by 2
  5. 2025Weakly-Supervised Domain Adaptation with Proportion-Constrained Pseudo-Labelingcited by 2
  6. 2024Learning from Concealed Labelscited by 0
  7. 2025Towards Privacy-Preserving Fine-Grained Visual Classification via Hierarchical Learning from Label Proportionscited by 0
  8. 2026Leveraging Label Proportion Prior for Class-Imbalanced Semi-Supervised Learningcited by 0