# Handling Inter-class and Intra-class Imbalance in Class-imbalanced Learning

arXiv: https://arxiv.org/abs/2111.12791 · HTML: https://mlsanity.com/paper/2111.12791/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 55 references that are in the map.
- First posted on arXiv 24 Nov 2021.

## Builds on (most cited first, 9 of 9)

- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Training Region-based Object Detectors with Online Hard Example Mining](https://mlsanity.com/paper/1604.03540/) (2016)
- [Libra R-CNN: Towards Balanced Learning for Object Detection](https://mlsanity.com/paper/1904.02701/) (2019)
- [Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning](https://mlsanity.com/paper/1609.06570/) (2016)
- [Imbalance Problems in Object Detection: A Review](https://mlsanity.com/paper/1909.00169/) (2019)
- [Class Rectification Hard Mining for Imbalanced Deep Learning](https://mlsanity.com/paper/1712.03162/) (2017)
- [Self-paced Ensemble for Highly Imbalanced Massive Data Classification](https://mlsanity.com/paper/1909.03500/) (2019)
- [MESA: Boost Ensemble Imbalanced Learning with MEta-SAmpler](https://mlsanity.com/paper/2010.08830/) (2020)
- [Combined Cleaning and Resampling Algorithm for Multi-Class Imbalanced Data with Label Noise](https://mlsanity.com/paper/2004.03406/) (2020)

## Built on by (most cited first, 5 of 5)

- [MC-ViViT: Multi-branch Classifier-ViViT to detect Mild Cognitive Impairment in older adults using facial videos](https://mlsanity.com/paper/2304.05292/) (2023)
- [If At First You Don't Succeed: Test Time Re-ranking for Zero-shot, Cross-domain Retrieval](https://mlsanity.com/paper/2303.17703/) (2023)
- [Deep learning enhanced mixed integer optimization: Learning to reduce model dimensionality](https://mlsanity.com/paper/2401.09556/) (2024)
- [Compositional Attribute Imbalance in Vision Datasets](https://mlsanity.com/paper/2506.14418/) (2025)
- [Multi-Level Analyzation of Imbalance to Resolve Non-IID-Ness in Federated Learning](https://mlsanity.com/paper/2606.10250/) (2026)

## Abstract (arXiv)

Class-imbalance is a common problem in machine learning practice. Typical Imbalanced Learning (IL) methods balance the data via intuitive class-wise resampling or reweighting. However, previous studies suggest that beyond class-imbalance, intrinsic data difficulty factors like overlapping, noise, and small disjuncts also play critical roles. To handle them, many solutions have been proposed (e.g., noise removal, borderline sampling, hard example mining) but are still confined to a specific factor and cannot generalize to broader scenarios, which raises an interesting question: how to handle both class-agnostic difficulties and the class-imbalance in a unified way? To answer this, we consider both class-imbalance and its orthogonal: intra-class imbalance, i.e., the imbalanced distribution over easy and hard samples. Such distribution naturally reflects the complex influence of class-agnostic intrinsic data difficulties thus providing a new unified view for identifying and handling these factors during learning. From this perspective, we discuss the pros and cons of existing IL solutions and further propose new balancing techniques for more robust and efficient IL. Finally, we wrap up all solutions into a generic ensemble IL framework, namely DuBE (Duple-Balanced Ensemble). It features explicit and efficient inter-&intra-class balancing as well as easy extension with standardized APIs. Extensive experiments validate the effectiveness of DuBE. Code, examples, and documentation are available at https://github.com/AnonAuthorAI/duplebalance and https://duplebalance.readthedocs.io.