# Exemplar-free Online Continual Learning

arXiv: https://arxiv.org/abs/2202.05491 · HTML: https://mlsanity.com/paper/2202.05491/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 27 references that are in the map.
- First posted on arXiv 11 Feb 2022.

## Builds on (most cited first, 18 of 18)

- [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)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [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)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (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)
- [Online Continual Learning with Maximally Interfered Retrieval](https://mlsanity.com/paper/1908.04742/) (2019)
- [Maintaining Discrimination and Fairness in Class Incremental Learning](https://mlsanity.com/paper/1911.07053/) (2019)
- [Memory Efficient Experience Replay for Streaming Learning](https://mlsanity.com/paper/1809.05922/) (2018)
- [Large Scale Visual Food Recognition](https://mlsanity.com/paper/2103.16107/) (2021)
- [Incremental Learning In Online Scenario](https://mlsanity.com/paper/2003.13191/) (2020)
- [Online Continual Learning For Visual Food Classification](https://mlsanity.com/paper/2108.06781/) (2021)
- [Unsupervised Continual Learning Via Pseudo Labels](https://mlsanity.com/paper/2104.07164/) (2021)
- [Online Continual Learning Via Candidates Voting](https://mlsanity.com/paper/2110.08855/) (2021)

## Built on by (most cited first, 18 of 18)

- [Online Prototype Learning for Online Continual Learning](https://mlsanity.com/paper/2308.00301/) (2023)
- [Convolutional Prompting meets Language Models for Continual Learning](https://mlsanity.com/paper/2403.20317/) (2024)
- [CL-LoRA: Continual Low-Rank Adaptation for Rehearsal-Free Class-Incremental Learning](https://mlsanity.com/paper/2505.24816/) (2025)
- [Long-tailed Food Classification](https://mlsanity.com/paper/2210.14748/) (2022)
- [Out-Of-Distribution Detection In Unsupervised Continual Learning](https://mlsanity.com/paper/2204.05462/) (2022)
- [DELTA: Decoupling Long-Tailed Online Continual Learning](https://mlsanity.com/paper/2404.04476/) (2024)
- [Simulating Personal Food Consumption Patterns using a Modified Markov Chain](https://mlsanity.com/paper/2208.06709/) (2022)
- [Exemplar-Free Continual Transformer with Convolutions](https://mlsanity.com/paper/2308.11357/) (2023)
- [An Improved Encoder-Decoder Framework for Food Energy Estimation](https://mlsanity.com/paper/2309.00468/) (2023)
- [AdaptCL: Adaptive Continual Learning for Tackling Heterogeneity in Sequential Datasets](https://mlsanity.com/paper/2207.11005/) (2022)
- [Diffusion Model with Clustering-based Conditioning for Food Image Generation](https://mlsanity.com/paper/2309.00199/) (2023)
- [Muti-Stage Hierarchical Food Classification](https://mlsanity.com/paper/2309.01075/) (2023)
- [Personalized Food Image Classification: Benchmark Datasets and New Baseline](https://mlsanity.com/paper/2309.08744/) (2023)
- [Learning to Classify New Foods Incrementally Via Compressed Exemplars](https://mlsanity.com/paper/2404.07507/) (2024)
- [Density Distribution-based Learning Framework for Addressing Online Continual Learning Challenges](https://mlsanity.com/paper/2311.13623/) (2023)
- [Continual learning via probabilistic exchangeable sequence modelling](https://mlsanity.com/paper/2503.20725/) (2025)
- [Memory-efficient Continual Learning with Prototypical Exemplar Condensation](https://mlsanity.com/paper/2603.13804/) (2026)
- [Adapter-Based Few-Shot Continual Learning for Malicious Packet Recognition](https://mlsanity.com/paper/2608.23536/) (2026)

## Abstract (arXiv)

Targeted for real world scenarios, online continual learning aims to learn new tasks from sequentially available data under the condition that each data is observed only once by the learner. Though recent works have made remarkable achievements by storing part of learned task data as exemplars for knowledge replay, the performance is greatly relied on the size of stored exemplars while the storage consumption is a significant constraint in continual learning. In addition, storing exemplars may not always be feasible for certain applications due to privacy concerns. In this work, we propose a novel exemplar-free method by leveraging nearest-class-mean (NCM) classifier where the class mean is estimated during training phase on all data seen so far through online mean update criteria. We focus on image classification task and conduct extensive experiments on benchmark datasets including CIFAR-100 and Food-1k. The results demonstrate that our method without using any exemplar outperforms state-of-the-art exemplar-based approaches with large margins under standard protocol (20 exemplars per class) and is able to achieve competitive performance even with larger exemplar size (100 exemplars per class).