# Online Continual Learning on a Contaminated Data Stream with Blurry Task Boundaries

arXiv: https://arxiv.org/abs/2203.15355 · HTML: https://mlsanity.com/paper/2203.15355/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 40 references that are in the map.
- First posted on arXiv 29 Mar 2022.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence](https://mlsanity.com/paper/1801.10112/) (2018)
- [An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks](https://mlsanity.com/paper/1312.6211/) (2013)
- [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://mlsanity.com/paper/2002.07394/) (2020)
- [MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels](https://mlsanity.com/paper/1712.05055/) (2017)
- [Learning from Noisy Labels with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2007.08199/) (2020)
- [Gradient based sample selection for online continual learning](https://mlsanity.com/paper/1903.08671/) (2019)
- [Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference](https://mlsanity.com/paper/1810.11910/) (2018)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [How does Disagreement Help Generalization against Label Corruption?](https://mlsanity.com/paper/1901.04215/) (2019)
- [Online Continual Learning with Maximally Interfered Retrieval](https://mlsanity.com/paper/1908.04742/) (2019)
- [Unsupervised Label Noise Modeling and Loss Correction](https://mlsanity.com/paper/1904.11238/) (2019)
- [Training Deep Neural Networks on Noisy Labels with Bootstrapping](https://mlsanity.com/paper/1412.6596/) (2014)
- [In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning](https://mlsanity.com/paper/2101.06329/) (2021)
- [Rainbow Memory: Continual Learning with a Memory of Diverse Samples](https://mlsanity.com/paper/2103.17230/) (2021)
- [WebVision Database: Visual Learning and Understanding from Web Data](https://mlsanity.com/paper/1708.02862/) (2017)
- [Automated Curriculum Learning for Neural Networks](https://mlsanity.com/paper/1704.03003/) (2017)
- [CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise](https://mlsanity.com/paper/1711.07131/) (2017)
- [SELF: Learning to Filter Noisy Labels with Self-Ensembling](https://mlsanity.com/paper/1910.01842/) (2019)
- [Online Coreset Selection for Rehearsal-based Continual Learning](https://mlsanity.com/paper/2106.01085/) (2021)
- [Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise](https://mlsanity.com/paper/2012.05458/) (2020)
- [NSML: Meet the MLaaS platform with a real-world case study](https://mlsanity.com/paper/1810.09957/) (2018)
- [Continual Learning on Noisy Data Streams via Self-Purified Replay](https://mlsanity.com/paper/2110.07735/) (2021)
- [Robust Learning by Self-Transition for Handling Noisy Labels](https://mlsanity.com/paper/2012.04337/) (2020)

## Built on by (most cited first, 30 of 31)

- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation](https://mlsanity.com/paper/2402.08712/) (2024)
- [Class Incremental Learning via Likelihood Ratio Based Task Prediction](https://mlsanity.com/paper/2309.15048/) (2023)
- [Rethinking Momentum Knowledge Distillation in Online Continual Learning](https://mlsanity.com/paper/2309.02870/) (2023)
- [Bayesian Learning-driven Prototypical Contrastive Loss for Class-Incremental Learning](https://mlsanity.com/paper/2405.11067/) (2024)
- [Gated Integration of Low-Rank Adaptation for Continual Learning of Large Language Models](https://mlsanity.com/paper/2505.15424/) (2025)
- [Online Continual Learning on Hierarchical Label Expansion](https://mlsanity.com/paper/2308.14374/) (2023)
- [Continual Learning for Predictive Maintenance: Overview and Challenges](https://mlsanity.com/paper/2301.12467/) (2023)
- [Class-incremental Learning for Time Series: Benchmark and Evaluation](https://mlsanity.com/paper/2402.12035/) (2024)
- [SimCS: Simulation for Domain Incremental Online Continual Segmentation](https://mlsanity.com/paper/2211.16234/) (2022)
- [Label Delay in Online Continual Learning](https://mlsanity.com/paper/2312.00923/) (2023)
- [Coherent Temporal Synthesis for Incremental Action Segmentation](https://mlsanity.com/paper/2403.06102/) (2024)
- [Active Learning for Continual Learning: Keeping the Past Alive in the Present](https://mlsanity.com/paper/2501.14278/) (2025)
- [Chunking: Continual Learning is not just about Distribution Shift](https://mlsanity.com/paper/2310.02206/) (2023)
- [Reinforced Interactive Continual Learning via Real-time Noisy Human Feedback](https://mlsanity.com/paper/2505.09925/) (2025)
- [Class-Incremental Learning Using Generative Experience Replay Based on Time-aware Regularization](https://mlsanity.com/paper/2310.03898/) (2023)
- [Lifelong Learning of Video Diffusion Models From a Single Video Stream](https://mlsanity.com/paper/2406.04814/) (2024)
- [May the Forgetting Be with You: Alternate Replay for Learning with Noisy Labels](https://mlsanity.com/paper/2408.14284/) (2024)
- [Continual Learning in the Presence of Spurious Correlation](https://mlsanity.com/paper/2303.11863/) (2023)
- [Self-Controlled Dynamic Expansion Model for Continual Learning](https://mlsanity.com/paper/2504.10561/) (2025)
- [Data Stream Sampling with Fuzzy Task Boundaries and Noisy Labels](https://mlsanity.com/paper/2404.04871/) (2024)
- [Anticipating Future Object Compositions without Forgetting](https://mlsanity.com/paper/2407.10723/) (2024)
- [Incrementally Learning Multiple Diverse Data Domains via Multi-Source Dynamic Expansion Model](https://mlsanity.com/paper/2501.08878/) (2025)
- [Towards Robust Incremental Learning under Ambiguous Supervision](https://mlsanity.com/paper/2501.13584/) (2025)
- [From Offline to Online Memory-Free and Task-Free Continual Learning via Fine-Grained Hypergradients](https://mlsanity.com/paper/2502.18762/) (2025)
- [Dynamic Dual Buffer with Divide-and-Conquer Strategy for Online Continual Learning](https://mlsanity.com/paper/2505.18101/) (2025)
- [Learning After Model Deployment](https://mlsanity.com/paper/2510.17160/) (2025)
- [Optimal Resource Allocation for ML Model Training and Deployment under Concept Drift](https://mlsanity.com/paper/2512.12816/) (2025)
- [Memory-efficient Continual Learning with Prototypical Exemplar Condensation](https://mlsanity.com/paper/2603.13804/) (2026)
- [Streaming Adversarial Robustness in Fuzzy ARTMAP: Mechanism-Aligned Evaluation, Progressive Training, and Interpretable Diagnostics](https://mlsanity.com/paper/2605.06902/) (2026)

## Abstract (arXiv)

Learning under a continuously changing data distribution with incorrect labels is a desirable real-world problem yet challenging. A large body of continual learning (CL) methods, however, assumes data streams with clean labels, and online learning scenarios under noisy data streams are yet underexplored. We consider a more practical CL task setup of an online learning from blurry data stream with corrupted labels, where existing CL methods struggle. To address the task, we first argue the importance of both diversity and purity of examples in the episodic memory of continual learning models. To balance diversity and purity in the episodic memory, we propose a novel strategy to manage and use the memory by a unified approach of label noise aware diverse sampling and robust learning with semi-supervised learning. Our empirical validations on four real-world or synthetic noise datasets (CIFAR10 and 100, mini-WebVision, and Food-101N) exhibit that our method significantly outperforms prior arts in this realistic and challenging continual learning scenario. Code and data splits are available in https://github.com/clovaai/puridiver.