mlsanityData to 7 Oct 2026

Task-Free Continual Learning

arXiv 1812.03596 ↗First posted 10 Dec 2018cs.CV cs.AI cs.LGcited by 219

Not on the map. Why?

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.

Key facts. Cited by 219 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 39; 2022: 35; 2023: 43; 2024: 47; 2025: 29; 2026: 26.

219 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  2. 2023The Curse of Recursion: Training on Generated Data Makes Models Forgetcited by 343
  3. 2021New Insights on Reducing Abrupt Representation Change in Online Continual Learningcited by 215
  4. 2023Class-Incremental Learning: A Surveycited by 209
  5. 2022Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networkscited by 126
  6. 2021Avalanche: an End-to-End Library for Continual Learningcited by 124
  7. 2022Continual Learning and Private Unlearningcited by 124
  8. 2024Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learningcited by 115
  9. 2022The CLEAR Benchmark: Continual LEArning on Real-World Imagerycited by 92
  10. 2023Learning without Forgetting for Vision-Language Modelscited by 79
  11. 2024Continual Learning and Catastrophic Forgettingcited by 73
  12. 2023OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensemblingcited by 71
38 more
  1. 2021Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Datacited by 67
  2. 2021Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inferencecited by 66
  3. 2023A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learningcited by 66
  4. 2023Continual Detection Transformer for Incremental Object Detectioncited by 59
  5. 2021Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworkscited by 56
  6. 2021Recent Advances of Continual Learning in Computer Vision: An Overviewcited by 55
  7. 2024Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learningcited by 49
  8. 2022Learning Fast and Slow for Online Time Series Forecastingcited by 43
  9. 2022Information-theoretic Online Memory Selection for Continual Learningcited by 42
  10. 2022Continual Normalization: Rethinking Batch Normalization for Online Continual Learningcited by 40
  11. 2021Class-Incremental Learning with Generative Classifierscited by 39
  12. 2021DualNet: Continual Learning, Fast and Slowcited by 39
  13. 2021Continually Learning Self-Supervised Representations with Projected Functional Regularizationcited by 38
  14. 2024Online DPO: Online Direct Preference Optimization with Fast-Slow Chasingcited by 38
  15. 2022On the Soft-Subnetwork for Few-shot Class Incremental Learningcited by 37
  16. 2023Test-Time Training on Video Streamscited by 37
  17. 2022CLAD: A realistic Continual Learning benchmark for Autonomous Drivingcited by 35
  18. 2021Continual Learning for Recurrent Neural Networks: an Empirical Evaluationcited by 34
  19. 2021Wanderlust: Online Continual Object Detection in the Real Worldcited by 34
  20. 2024Convolutional Prompting meets Language Models for Continual Learningcited by 32
  21. 2024Unsupervised Continual Anomaly Detection with Contrastively-learned Promptcited by 31
  22. 2021How Well Does Self-Supervised Pre-Training Perform with Streaming Data?cited by 29
  23. 2022Improving Task-free Continual Learning by Distributionally Robust Memory Evolutioncited by 29
  24. 2023Probabilistic Bilevel Coreset Selectioncited by 26
  25. 2024Online-LoRA: Task-free Online Continual Learning via Low Rank Adaptationcited by 26
  26. 2021Continual Semi-Supervised Learning through Contrastive Interpolation Consistencycited by 25
  27. 2022Continual Object Detection: A review of definitions, strategies, and challengescited by 25
  28. 2022Few-Shot Continual Active Learning by a Robotcited by 24
  29. 2021Is Class-Incremental Enough for Continual Learning?cited by 22
  30. 2022Task-Free Continual Learning via Online Discrepancy Distance Learningcited by 22
  31. 2023Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learningcited by 21
  32. 2024Online Continual Learning For Interactive Instruction Following Agentscited by 21
  33. 2021Sequoia: A Software Framework to Unify Continual Learning Researchcited by 19
  34. 2021Prototype-Guided Memory Replay for Continual Learningcited by 19
  35. 2024Eliciting the Priors of Large Language Models using Iterated In-Context Learningcited by 19
  36. 2021Unsupervised Continual Learning Via Pseudo Labelscited by 18
  37. 2021Class-Incremental Experience Replay for Continual Learning under Concept Driftcited by 17
  38. 2021Encoders and Ensembles for Task-Free Continual Learningcited by 17

50 most cited of 219 All 219 (JSON)