mlsanityData to 7 Oct 2026

Toward Robustness in Multi-label Classification: A Data Augmentation Strategy against Imbalance and Noise

arXiv 2312.07087 ↗First posted 12 Dec 2023cs.LG cs.AIcited by 11

Not on the map. Why?

Abstract (arXiv)

Multi-label classification poses challenges due to imbalanced and noisy labels in training data. We propose a unified data augmentation method, named BalanceMix, to address these challenges. Our approach includes two samplers for imbalanced labels, generating minority-augmented instances with high diversity. It also refines multi-labels at the label-wise granularity, categorizing noisy labels as clean, re-labeled, or ambiguous for robust optimization. Extensive experiments on three benchmark datasets demonstrate that BalanceMix outperforms existing state-of-the-art methods. We release the code at https://github.com/DISL-Lab/BalanceMix.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 23 of its 43 references that are in the map. First posted on arXiv 12 Dec 2023.

Builds on

23 of 43 references.

References · 23

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  3. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  4. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  5. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
  6. 2020Asymmetric Loss For Multi-Label Classificationcited by 379
  7. 2021Distribution Alignment: A Unified Framework for Long-tail Visual Recognitioncited by 198
  8. 2020General Multi-label Image Classification with Transformerscited by 126
  9. 2021Query2Label: A Simple Transformer Way to Multi-Label Classificationcited by 126
  10. 2019Learning a Deep ConvNet for Multi-label Classification with Partial Labelscited by 124
  11. 2020Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasetscited by 122
  12. 2021Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspectivecited by 116
11 more
  1. 2021Understanding and Improving Early Stopping for Learning with Noisy Labelscited by 112
  2. 2021The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classificationcited by 100
  3. 2020Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noisecited by 82
  4. 2021Multi-Label Learning from Single Positive Labelscited by 81
  5. 2021ML-Decoder: Scalable and Versatile Classification Headcited by 78
  6. 2021Balanced-MixUp for Highly Imbalanced Medical Image Classificationcited by 46
  7. 2021Robust Long-Tailed Learning under Label Noisecited by 35
  8. 2023Fine-Grained Classification with Noisy Labelscited by 15
  9. 2021Evaluating Multi-label Classifiers with Noisy Labelscited by 9
  10. 2023SuperDisco: Super-Class Discovery Improves Visual Recognition for the Long-Tailcited by 9
  11. 2022Multi-class Label Noise Learning via Loss Decomposition and Centroid Estimationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 3; 2026: 4.

11 papers.

  1. 2025Curiosity Meets Cooperation: A Game-Theoretic Approach to Long-Tail Multi-Label Learningcited by 4
  2. 2024Ensemble Methods for Sequence Classification with Hidden Markov Modelscited by 1
  3. 2024A Bilevel Optimization Framework for Imbalanced Data Classificationcited by 1
  4. 2026Model-Agnostic Meta Learning for Class Imbalance Adaptationcited by 1
  5. 2024Free Performance Gain from Mixing Multiple Partially Labeled Samples in Multi-label Image Classificationcited by 0
  6. 2024A Survey on Incomplete Multi-label Learning: Recent Advances and Future Trendscited by 0
  7. 2025Sampling Imbalanced Data with Multi-objective Bilevel Optimizationcited by 0
  8. 2025On the Performance of Concept Probing: The Influence of the Data (Extended Version)cited by 0
  9. 2026Noise-Adaptive Regularization for Robust Multi-Label Remote Sensing Image Classificationcited by 0
  10. 2026A Scalable Curiosity-Driven Game-Theoretic Framework for Long-Tail Multi-Label Learning in Data Miningcited by 0
  11. 2026Addressing Imbalance in Multi-Label Data via Label-Specific Distance-based Oversamplingcited by 0