# Multi-Granularity Regularized Re-Balancing for Class Incremental Learning

arXiv: https://arxiv.org/abs/2206.15189 · HTML: https://mlsanity.com/paper/2206.15189/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 58 references that are in the map.
- First posted on arXiv 30 Jun 2022.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018)
- [Class-incremental learning: survey and performance evaluation on image classification](https://mlsanity.com/paper/2010.15277/) (2020)
- [BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/1912.02413/) (2019)
- [DER: Dynamically Expandable Representation for Class Incremental Learning](https://mlsanity.com/paper/2103.16788/) (2021)
- [Equalization Loss for Long-Tailed Object Recognition](https://mlsanity.com/paper/2003.05176/) (2020)
- [Rainbow Memory: Continual Learning with a Memory of Diverse Samples](https://mlsanity.com/paper/2103.17230/) (2021)
- [Mnemonics Training: Multi-Class Incremental Learning without Forgetting](https://mlsanity.com/paper/2002.10211/) (2020)
- [Class-incremental Learning via Deep Model Consolidation](https://mlsanity.com/paper/1903.07864/) (2019)
- [Using Hindsight to Anchor Past Knowledge in Continual Learning](https://mlsanity.com/paper/2002.08165/) (2020)
- [Adaptive Aggregation Networks for Class-Incremental Learning](https://mlsanity.com/paper/2010.05063/) (2020)
- [Making Better Mistakes: Leveraging Class Hierarchies with Deep Networks](https://mlsanity.com/paper/1912.09393/) (2019)
- [On Learning the Geodesic Path for Incremental Learning](https://mlsanity.com/paper/2104.08572/) (2021)
- [Efficient Feature Transformations for Discriminative and Generative Continual Learning](https://mlsanity.com/paper/2103.13558/) (2021)
- [Curriculum-Meta Learning for Order-Robust Continual Relation Extraction](https://mlsanity.com/paper/2101.01926/) (2021)
- [Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing](https://mlsanity.com/paper/2103.04570/) (2021)
- [Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification](https://mlsanity.com/paper/2112.07928/) (2021)

## Built on by (most cited first, 8 of 8)

- [A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends](https://mlsanity.com/paper/2402.15490/) (2024)
- [Heterogeneous Forgetting Compensation for Class-Incremental Learning](https://mlsanity.com/paper/2308.03374/) (2023)
- [Reshaping the Online Data Buffering and Organizing Mechanism for Continual Test-Time Adaptation](https://mlsanity.com/paper/2407.09367/) (2024)
- [Reducing Class-wise Confusion for Incremental Learning with Disentangled Manifolds](https://mlsanity.com/paper/2503.17677/) (2025)
- [Hessian Aware Low-Rank Perturbation for Order-Robust Continual Learning](https://mlsanity.com/paper/2311.15161/) (2023)
- [Few-shot Class-incremental Fault Diagnosis by Preserving Class-Agnostic Knowledge with Dual-Granularity Representations](https://mlsanity.com/paper/2508.16634/) (2025)
- [Causally Sufficient and Necessary Feature Expansion for Class-Incremental Learning](https://mlsanity.com/paper/2603.09145/) (2026)
- [FeDMRA: Federated Incremental Learning with Dynamic Memory Replay Allocation](https://mlsanity.com/paper/2603.28455/) (2026)

## Abstract (arXiv)

Deep learning models suffer from catastrophic forgetting when learning new tasks incrementally. Incremental learning has been proposed to retain the knowledge of old classes while learning to identify new classes. A typical approach is to use a few exemplars to avoid forgetting old knowledge. In such a scenario, data imbalance between old and new classes is a key issue that leads to performance degradation of the model. Several strategies have been designed to rectify the bias towards the new classes due to data imbalance. However, they heavily rely on the assumptions of the bias relation between old and new classes. Therefore, they are not suitable for complex real-world applications. In this study, we propose an assumption-agnostic method, Multi-Granularity Regularized re-Balancing (MGRB), to address this problem. Re-balancing methods are used to alleviate the influence of data imbalance; however, we empirically discover that they would under-fit new classes. To this end, we further design a novel multi-granularity regularization term that enables the model to consider the correlations of classes in addition to re-balancing the data. A class hierarchy is first constructed by grouping the semantically or visually similar classes. The multi-granularity regularization then transforms the one-hot label vector into a continuous label distribution, which reflects the relations between the target class and other classes based on the constructed class hierarchy. Thus, the model can learn the inter-class relational information, which helps enhance the learning of both old and new classes. Experimental results on both public datasets and a real-world fault diagnosis dataset verify the effectiveness of the proposed method.