# Task-Free Continual Learning

arXiv: https://arxiv.org/abs/1812.03596 · HTML: https://mlsanity.com/paper/1812.03596/

## Key facts

- Cited by 221 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Dec 2018.

## Built on by (most cited first, 30 of 221)

- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [The Curse of Recursion: Training on Generated Data Makes Models Forget](https://mlsanity.com/paper/2305.17493/) (2023)
- [New Insights on Reducing Abrupt Representation Change in Online Continual Learning](https://mlsanity.com/paper/2104.05025/) (2021)
- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [Continual Learning and Private Unlearning](https://mlsanity.com/paper/2203.12817/) (2022)
- [Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks](https://mlsanity.com/paper/2207.13243/) (2022)
- [Avalanche: an End-to-End Library for Continual Learning](https://mlsanity.com/paper/2104.00405/) (2021)
- [Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning](https://mlsanity.com/paper/2403.12030/) (2024)
- [The CLEAR Benchmark: Continual LEArning on Real-World Imagery](https://mlsanity.com/paper/2201.06289/) (2022)
- [Learning without Forgetting for Vision-Language Models](https://mlsanity.com/paper/2305.19270/) (2023)
- [Continual Learning and Catastrophic Forgetting](https://mlsanity.com/paper/2403.05175/) (2024)
- [OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling](https://mlsanity.com/paper/2309.12659/) (2023)
- [Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Data](https://mlsanity.com/paper/2108.09020/) (2021)
- [A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning](https://mlsanity.com/paper/2307.09218/) (2023)
- [Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference](https://mlsanity.com/paper/2110.10031/) (2021)
- [Continual Detection Transformer for Incremental Object Detection](https://mlsanity.com/paper/2304.03110/) (2023)
- [Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworks](https://mlsanity.com/paper/2105.12374/) (2021)
- [Recent Advances of Continual Learning in Computer Vision: An Overview](https://mlsanity.com/paper/2109.11369/) (2021)
- [Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning](https://mlsanity.com/paper/2404.00781/) (2024)
- [Learning Fast and Slow for Online Time Series Forecasting](https://mlsanity.com/paper/2202.11672/) (2022)
- [Information-theoretic Online Memory Selection for Continual Learning](https://mlsanity.com/paper/2204.04763/) (2022)
- [Continual Normalization: Rethinking Batch Normalization for Online Continual Learning](https://mlsanity.com/paper/2203.16102/) (2022)
- [Class-Incremental Learning with Generative Classifiers](https://mlsanity.com/paper/2104.10093/) (2021)
- [DualNet: Continual Learning, Fast and Slow](https://mlsanity.com/paper/2110.00175/) (2021)
- [Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing](https://mlsanity.com/paper/2406.05534/) (2024)
- [Continually Learning Self-Supervised Representations with Projected Functional Regularization](https://mlsanity.com/paper/2112.15022/) (2021)
- [On the Soft-Subnetwork for Few-shot Class Incremental Learning](https://mlsanity.com/paper/2209.07529/) (2022)
- [Test-Time Training on Video Streams](https://mlsanity.com/paper/2307.05014/) (2023)
- [CLAD: A realistic Continual Learning benchmark for Autonomous Driving](https://mlsanity.com/paper/2210.03482/) (2022)
- [Continual Learning for Recurrent Neural Networks: an Empirical Evaluation](https://mlsanity.com/paper/2103.07492/) (2021)

## Abstract (arXiv)

Methods proposed in the literature towards continual deep learning typically operate in a task-based sequential learning setup. A sequence of tasks is learned, one at a time, with all data of current task available but not of previous or future tasks. Task boundaries and identities are known at all times. This setup, however, is rarely encountered in practical applications. Therefore we investigate how to transform continual learning to an online setup. We develop a system that keeps on learning over time in a streaming fashion, with data distributions gradually changing and without the notion of separate tasks. To this end, we build on the work on Memory Aware Synapses, and show how this method can be made online by providing a protocol to decide i) when to update the importance weights, ii) which data to use to update them, and iii) how to accumulate the importance weights at each update step. Experimental results show the validity of the approach in the context of two applications: (self-)supervised learning of a face recognition model by watching soap series and learning a robot to avoid collisions.