mlsanityData to 7 Oct 2026

Continual Learning Based on OOD Detection and Task Masking

arXiv 2203.09450 ↗First posted 17 Mar 2022cs.CV cs.LGcited by 21

Not on the map. Why?

Abstract (arXiv)

Existing continual learning techniques focus on either task incremental learning (TIL) or class incremental learning (CIL) problem, but not both. CIL and TIL differ mainly in that the task-id is provided for each test sample during testing for TIL, but not provided for CIL. Continual learning methods intended for one problem have limitations on the other problem. This paper proposes a novel unified approach based on out-of-distribution (OOD) detection and task masking, called CLOM, to solve both problems. The key novelty is that each task is trained as an OOD detection model rather than a traditional supervised learning model, and a task mask is trained to protect each task to prevent forgetting. Our evaluation shows that CLOM outperforms existing state-of-the-art baselines by large margins. The average TIL/CIL accuracy of CLOM over six experiments is 87.6/67.9% while that of the best baselines is only 82.4/55.0%.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 61 of its 83 references that are in the map. First posted on arXiv 17 Mar 2022.

Builds on

61 of 83 references.

References · 61

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  6. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  7. 2014Going Deeper with Convolutionscited by 4,231
  8. 2020Supervised Contrastive Learningcited by 2,803
  9. 2016Learning without Forgettingcited by 2,465
  10. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  11. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  12. 2016Progressive Neural Networkscited by 1,332
38 more
  1. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  2. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
  3. 2017Continual Learning with Deep Generative Replaycited by 1,152
  4. 2018Experience Replay for Continual Learningcited by 1,074
  5. 2018Efficient Lifelong Learning with A-GEMcited by 1,044
  6. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 895
  7. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 882
  8. 2019Large Scale Incremental Learningcited by 727
  9. 2018Overcoming catastrophic forgetting with hard attention to the taskcited by 672
  10. 2019Three scenarios for continual learningcited by 610
  11. 2018End-to-End Incremental Learningcited by 596
  12. 2017Large Batch Training of Convolutional Networkscited by 529
  13. 2018Progress & Compress: A scalable framework for continual learningcited by 516
  14. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  15. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  16. 2016Expert Gate: Lifelong Learning with a Network of Expertscited by 369
  17. 2017PathNet: Evolution Channels Gradient Descent in Super Neural Networkscited by 362
  18. 2018Recent Advances in Open Set Recognition: A Surveycited by 309
  19. 2019Maintaining Discrimination and Fairness in Class Incremental Learningcited by 281
  20. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  21. 2019Continual learning with hypernetworkscited by 267
  22. 2018Learning without Memorizingcited by 249
  23. 2021Co2L: Contrastive Continual Learningcited by 243
  24. 2020Supermasks in Superpositioncited by 223
  25. 2020Mnemonics Training: Multi-Class Incremental Learning without Forgettingcited by 220
  26. 2019Compacting, Picking and Growing for Unforgetting Continual Learningcited by 207
  27. 2018Online Structured Laplace Approximations For Overcoming Catastrophic Forgettingcited by 197
  28. 2019REMIND Your Neural Network to Prevent Catastrophic Forgettingcited by 197
  29. 2019Episodic Memory in Lifelong Language Learningcited by 188
  30. 2018Reinforced Continual Learningcited by 186
  31. 2019Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learningcited by 181
  32. 2018Continual Learning of Context-dependent Processing in Neural Networkscited by 178
  33. 2017FearNet: Brain-Inspired Model for Incremental Learningcited by 177
  34. 2020Adaptive Aggregation Networks for Class-Incremental Learningcited by 149
  35. 2019Uncertainty-based Continual Learning with Adaptive Regularizationcited by 144
  36. 2019Scalable and Order-robust Continual Learning with Additive Parameter Decompositioncited by 125
  37. 2020Conditional Channel Gated Networks for Task-Aware Continual Learningcited by 115
  38. 2019Overcoming Catastrophic Forgetting with Unlabeled Data in the Wildcited by 111

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 7; 2024: 5; 2025: 2; 2026: 5.

21 papers.

Sort:

By area:

  1. 2022A Theoretical Study on Solving Continual Learningcited by 78
  2. 2023A Survey on Out-of-Distribution Detection in NLPcited by 31
  3. 2022A Multi-Head Model for Continual Learning via Out-of-Distribution Replaycited by 27
  4. 2023Open-World Continual Learning: Unifying Novelty Detection and Continual Learningcited by 22
  5. 2023Prediction Error-based Classification for Class-Incremental Learningcited by 14
  6. 2023Continual Evidential Deep Learning for Out-of-Distribution Detectioncited by 11
  7. 2024Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learningcited by 11
  8. 2024Continual Learning in the Presence of Repetitioncited by 10
  9. 2025On the Discrimination and Consistency for Exemplar-Free Class Incremental Learningcited by 8
  10. 2024Statistical Context Detection for Deep Lifelong Reinforcement Learningcited by 6
  11. 2023Look At Me, No Replay! SurpriseNet: Anomaly Detection Inspired Class Incremental Learningcited by 2
  12. 2026SLE-FNO: Single-Layer Extensions for Task-Agnostic Continual Learning in Fourier Neural Operatorscited by 2
9 more
  1. 2023HAT-CL: A Hard-Attention-to-the-Task PyTorch Library for Continual Learningcited by 1
  2. 2023Concept Matching: Clustering-based Federated Continual Learningcited by 1
  3. 2024Remembering Transformer for Continual Learningcited by 1
  4. 2025Task-Agnostic Federated Continual Learning via Replay-Free Gradient Projectioncited by 1
  5. 2024Confidence-Based Task Prediction in Continual Disease Classification Using Probability Distributioncited by 0
  6. 2026Similarity-Aware Mixture-of-Experts for Data-Efficient Continual Learningcited by 0
  7. 2026GR4CIL: Gap-compensated Routing for CLIP-based Class Incremental Learningcited by 0
  8. 2026Separating Expert Retention from Autonomous Source Inference in Raw-ECG-Replay-Free Continual ECG Deploymentcited by 0
  9. 2026TOOD: Task-Aware Out-of-Distribution Score Calibration for Continual Learnerscited by 0