# A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning

arXiv: https://arxiv.org/abs/2205.13218 · HTML: https://mlsanity.com/paper/2205.13218/

## Key facts

- Cited by 154 papers in the map (data through 14 Oct 2026).
- Builds on 68 of its 95 references that are in the map.
- First posted on arXiv 26 May 2022.

## Builds on (most cited first, 30 of 68)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [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)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [Overcoming catastrophic forgetting with hard attention to the task](https://mlsanity.com/paper/1801.01423/) (2018)
- [Wasserstein GAN](https://mlsanity.com/paper/1701.07875/) (2017)
- [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)
- [Expert Gate: Lifelong Learning with a Network of Experts](https://mlsanity.com/paper/1611.06194/) (2016)
- [DER: Dynamically Expandable Representation for Class Incremental Learning](https://mlsanity.com/paper/2103.16788/) (2021)
- [Recent Advances in Open Set Recognition: A Survey](https://mlsanity.com/paper/1811.08581/) (2018)
- [On Tiny Episodic Memories in Continual Learning](https://mlsanity.com/paper/1902.10486/) (2019)

## Built on by (most cited first, 30 of 154)

- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need](https://mlsanity.com/paper/2303.07338/) (2023)
- [Continual Learning with Pre-Trained Models: A Survey](https://mlsanity.com/paper/2401.16386/) (2024)
- [Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning](https://mlsanity.com/paper/2403.12030/) (2024)
- [FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning](https://mlsanity.com/paper/2309.14062/) (2023)
- [Learning without Forgetting for Vision-Language Models](https://mlsanity.com/paper/2305.19270/) (2023)
- [A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning](https://mlsanity.com/paper/2307.09218/) (2023)
- [PILOT: A Pre-Trained Model-Based Continual Learning Toolbox](https://mlsanity.com/paper/2309.07117/) (2023)
- [Elastic Feature Consolidation for Cold Start Exemplar-Free Incremental Learning](https://mlsanity.com/paper/2402.03917/) (2024)
- [Make Continual Learning Stronger via C-Flat](https://mlsanity.com/paper/2404.00986/) (2024)
- [SIESTA: Efficient Online Continual Learning with Sleep](https://mlsanity.com/paper/2303.10725/) (2023)
- [Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy](https://mlsanity.com/paper/2312.10549/) (2023)
- [Online Continual Learning For Interactive Instruction Following Agents](https://mlsanity.com/paper/2403.07548/) (2024)
- [Integrating Task-Specific and Universal Adapters for Pre-Trained Model-based Class-Incremental Learning](https://mlsanity.com/paper/2508.08165/) (2025)
- [Adapter Merging with Centroid Prototype Mapping for Scalable Class-Incremental Learning](https://mlsanity.com/paper/2412.18219/) (2024)
- [Revisiting Neural Networks for Continual Learning: An Architectural Perspective](https://mlsanity.com/paper/2404.14829/) (2024)
- [Dual Consolidation for Pre-Trained Model-Based Domain-Incremental Learning](https://mlsanity.com/paper/2410.00911/) (2024)
- [CoLeCLIP: Open-Domain Continual Learning via Joint Task Prompt and Vocabulary Learning](https://mlsanity.com/paper/2403.10245/) (2024)
- [Task-Agnostic Guided Feature Expansion for Class-Incremental Learning](https://mlsanity.com/paper/2503.00823/) (2025)
- [Wakening Past Concepts without Past Data: Class-Incremental Learning from Online Placebos](https://mlsanity.com/paper/2310.16115/) (2023)
- [Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective](https://mlsanity.com/paper/2506.03951/) (2025)
- [Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learning](https://mlsanity.com/paper/2509.16738/) (2025)
- [Bayesian Learning-driven Prototypical Contrastive Loss for Class-Incremental Learning](https://mlsanity.com/paper/2405.11067/) (2024)
- [Dynamic Integration of Task-Specific Adapters for Class Incremental Learning](https://mlsanity.com/paper/2409.14983/) (2024)
- [Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts](https://mlsanity.com/paper/2507.07100/) (2025)
- [Hyperparameters in Continual Learning: A Reality Check](https://mlsanity.com/paper/2403.09066/) (2024)
- [Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learning](https://mlsanity.com/paper/2409.19245/) (2024)
- [Random Representations Outperform Online Continually Learned Representations](https://mlsanity.com/paper/2402.08823/) (2024)
- [Theoretical Insights into Overparameterized Models in Multi-Task and Replay-Based Continual Learning](https://mlsanity.com/paper/2408.16939/) (2024)
- [Forget Forgetting: Continual Learning in a World of Abundant Memory](https://mlsanity.com/paper/2502.07274/) (2025)

## Abstract (arXiv)

Real-world applications require the classification model to adapt to new classes without forgetting old ones. Correspondingly, Class-Incremental Learning (CIL) aims to train a model with limited memory size to meet this requirement. Typical CIL methods tend to save representative exemplars from former classes to resist forgetting, while recent works find that storing models from history can substantially boost the performance. However, the stored models are not counted into the memory budget, which implicitly results in unfair comparisons. We find that when counting the model size into the total budget and comparing methods with aligned memory size, saving models do not consistently work, especially for the case with limited memory budgets. As a result, we need to holistically evaluate different CIL methods at different memory scales and simultaneously consider accuracy and memory size for measurement. On the other hand, we dive deeply into the construction of the memory buffer for memory efficiency. By analyzing the effect of different layers in the network, we find that shallow and deep layers have different characteristics in CIL. Motivated by this, we propose a simple yet effective baseline, denoted as MEMO for Memory-efficient Expandable MOdel. MEMO extends specialized layers based on the shared generalized representations, efficiently extracting diverse representations with modest cost and maintaining representative exemplars. Extensive experiments on benchmark datasets validate MEMO's competitive performance. Code is available at: https://github.com/wangkiw/ICLR23-MEMO