# Incremental Learning with Maximum Entropy Regularization: Rethinking Forgetting and Intransigence

arXiv: https://arxiv.org/abs/1902.00829 · HTML: https://mlsanity.com/paper/1902.00829/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Feb 2019.

## Built on by (most cited first, 12 of 12)

- [Curriculum Learning: A Survey](https://mlsanity.com/paper/2101.10382/) (2021)
- [Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference](https://mlsanity.com/paper/2110.10031/) (2021)
- [Tackling Catastrophic Forgetting and Background Shift in Continual Semantic Segmentation](https://mlsanity.com/paper/2106.15287/) (2021)
- [Towards Unsupervised Open World Semantic Segmentation](https://mlsanity.com/paper/2201.01073/) (2022)
- [Incremental Learning for Heterogeneous Structure Segmentation in Brain Tumor MRI](https://mlsanity.com/paper/2305.19404/) (2023)
- [Online Continual Learning via the Meta-learning Update with Multi-scale Knowledge Distillation and Data Augmentation](https://mlsanity.com/paper/2209.06107/) (2022)
- [Detecting and Learning the Unknown in Semantic Segmentation](https://mlsanity.com/paper/2202.08700/) (2022)
- [Exploring Stability-Plasticity Trade-offs for Continual Named Entity Recognition](https://mlsanity.com/paper/2508.03259/) (2025)
- [Online Clustering of Seafloor Imagery for Interpretation during Long-Term AUV Operations](https://mlsanity.com/paper/2509.06678/) (2025)
- [Lower Difficulty and Better Robustness: A Bregman Divergence Perspective for Adversarial Training](https://mlsanity.com/paper/2208.12511/) (2022)
- [CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection](https://mlsanity.com/paper/2504.01882/) (2025)
- [Type-Balanced Contextual Learning for Incremental Named Entity Recognition](https://mlsanity.com/paper/2608.31038/) (2026)

## Abstract (arXiv)

Incremental learning suffers from two challenging problems; forgetting of old knowledge and intransigence on learning new knowledge. Prediction by the model incrementally learned with a subset of the dataset are thus uncertain and the uncertainty accumulates through the tasks by knowledge transfer. To prevent overfitting to the uncertain knowledge, we propose to penalize confident fitting to the uncertain knowledge by the Maximum Entropy Regularizer (MER). Additionally, to reduce class imbalance and induce a self-paced curriculum on new classes, we exclude a few samples from the new classes in every mini-batch, which we call DropOut Sampling (DOS). We further rethink evaluation metrics for forgetting and intransigence in incremental learning by tracking each sample's confusion at the transition of a task since the existing metrics that compute the difference in accuracy are often misleading. We show that the proposed method, named 'MEDIC', outperforms the state-of-the-art incremental learning algorithms in accuracy, forgetting, and intransigence measured by both the existing and the proposed metrics by a large margin in extensive empirical validations on CIFAR100 and a popular subset of ImageNet dataset (TinyImageNet).