# Class-Incremental Learning with Repetition

arXiv: https://arxiv.org/abs/2301.11396 · HTML: https://mlsanity.com/paper/2301.11396/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 38 references that are in the map.
- First posted on arXiv 26 Jan 2023.

## Builds on (most cited first, 23 of 23)

- [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)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [Three scenarios for continual learning](https://mlsanity.com/paper/1904.07734/) (2019)
- [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018)
- [Gradient based sample selection for online continual learning](https://mlsanity.com/paper/1903.08671/) (2019)
- [Rainbow Memory: Continual Learning with a Memory of Diverse Samples](https://mlsanity.com/paper/2103.17230/) (2021)
- [New Insights on Reducing Abrupt Representation Change in Online Continual Learning](https://mlsanity.com/paper/2104.05025/) (2021)
- [Continual Prototype Evolution: Learning Online from Non-Stationary Data Streams](https://mlsanity.com/paper/2009.00919/) (2020)
- [Avalanche: an End-to-End Library for Continual Learning](https://mlsanity.com/paper/2104.00405/) (2021)
- [Continuous Learning in Single-Incremental-Task Scenarios](https://mlsanity.com/paper/1806.08568/) (2018)
- [Imbalanced Continual Learning with Partitioning Reservoir Sampling](https://mlsanity.com/paper/2009.03632/) (2020)
- [Replay in Deep Learning: Current Approaches and Missing Biological Elements](https://mlsanity.com/paper/2104.04132/) (2021)
- [Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference](https://mlsanity.com/paper/2110.10031/) (2021)
- [Rehearsal-Free Continual Learning over Small Non-I.I.D. Batches](https://mlsanity.com/paper/1907.03799/) (2019)
- [Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition](https://mlsanity.com/paper/1905.12019/) (2019)
- [Is Class-Incremental Enough for Continual Learning?](https://mlsanity.com/paper/2112.02925/) (2021)

## Built on by (most cited first, 9 of 9)

- [Continual Learning and Catastrophic Forgetting](https://mlsanity.com/paper/2403.05175/) (2024)
- [Continual Learning in the Presence of Repetition](https://mlsanity.com/paper/2405.04101/) (2024)
- [Adaptive Hyperparameter Optimization for Continual Learning Scenarios](https://mlsanity.com/paper/2403.07015/) (2024)
- [Holistic Continual Learning under Concept Drift with Adaptive Memory Realignment](https://mlsanity.com/paper/2507.02310/) (2025)
- [Incremental Learning with Repetition via Pseudo-Feature Projection](https://mlsanity.com/paper/2502.19922/) (2025)
- [C2FL: Clustered Continual Federated Learning under Spatial and Temporal Drift](https://mlsanity.com/paper/2606.18003/) (2026)
- [Continual Learning by Three-Phase Consolidation](https://mlsanity.com/paper/2403.14679/) (2024)
- [Recommendation of data-free class-incremental learning algorithms by simulating future data](https://mlsanity.com/paper/2403.18132/) (2024)
- [Multi-Level Knowledge Distillation and Dynamic Self-Supervised Learning for Continual Learning](https://mlsanity.com/paper/2508.12692/) (2025)

## Abstract (arXiv)

Real-world data streams naturally include the repetition of previous concepts. From a Continual Learning (CL) perspective, repetition is a property of the environment and, unlike replay, cannot be controlled by the agent. Nowadays, the Class-Incremental (CI) scenario represents the leading test-bed for assessing and comparing CL strategies. This scenario type is very easy to use, but it never allows revisiting previously seen classes, thus completely neglecting the role of repetition. We focus on the family of Class-Incremental with Repetition (CIR) scenario, where repetition is embedded in the definition of the stream. We propose two stochastic stream generators that produce a wide range of CIR streams starting from a single dataset and a few interpretable control parameters. We conduct the first comprehensive evaluation of repetition in CL by studying the behavior of existing CL strategies under different CIR streams. We then present a novel replay strategy that exploits repetition and counteracts the natural imbalance present in the stream. On both CIFAR100 and TinyImageNet, our strategy outperforms other replay approaches, which are not designed for environments with repetition.