Toward Robustness in Multi-label Classification: A Data Augmentation Strategy against Imbalance and Noise
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.
Code (1)
Tasks
Data AugmentationDiversityMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATIONSimilar Papers 제목 키워드 기반
Improving Black-box Robustness with In-Context Rewriting
Machine learning models for text classification often excel on in-distribution (ID) data but struggle with unseen out-of-distribution (OOD) inputs. Most techniques for improving OOD robustness are not applicable to setti…
News Classificationtext-classificationText ClassificationCXR-LT 2026 Challenge: Projection-Aware Multi-Label and Zero-Shot Chest X-Ray Classification
This challenge tackles multi-label classification for known chest X-ray (CXR) lesions and zero-shot classification for unseen ones. To handle diverse CXR projections, we integrate projection-specific models via a classif…
Multi-Label ClassificationZero-shot GeneralizationContrastive LearningFine-Grained AutoAugmentation for Multi-Label Classification
Data augmentation is a commonly used approach to improving the generalization of deep learning models. Recent works show that learned data augmentation policies can achieve better generalization than hand-crafted ones. H…
ClassificationData AugmentationMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATION+2SGD-Mix: Enhancing Domain-Specific Image Classification with Label-Preserving Data Augmentation
Data augmentation for domain-specific image classification tasks often struggles to simultaneously address diversity, faithfulness, and label clarity of generated data, leading to suboptimal performance in downstream tas…
Data AugmentationDiversityimage-classificationImage ClassificationWhich Augmentation Should I Use? An Empirical Investigation of Augmentations for Self-Supervised Phonocardiogram Representation Learning
Despite recent advancements in deep learning, its application in real-world medical settings, such as phonocardiogram (PCG) classification, remains limited. A significant barrier is the lack of high-quality annotated dat…
Contrastive LearningRepresentation LearningSelf-Supervised Learning