mlsanityData to 7 Oct 2026

Generative Models from the perspective of Continual Learning

arXiv 1812.09111 ↗First posted 21 Dec 2018cs.LG cs.AI cs.CVcited by 69

Not on the map. Why?

Abstract (arXiv)

Which generative model is the most suitable for Continual Learning? This paper aims at evaluating and comparing generative models on disjoint sequential image generation tasks. We investigate how several models learn and forget, considering various strategies: rehearsal, regularization, generative replay and fine-tuning. We used two quantitative metrics to estimate the generation quality and memory ability. We experiment with sequential tasks on three commonly used benchmarks for Continual Learning (MNIST, Fashion MNIST and CIFAR10). We found that among all models, the original GAN performs best and among Continual Learning strategies, generative replay outperforms all other methods. Even if we found satisfactory combinations on MNIST and Fashion MNIST, training generative models sequentially on CIFAR10 is particularly instable, and remains a challenge. Our code is available online footnoteurlhttps://github.com/TLESORT/GenerativeContinualLearning.

Key facts. Cited by 69 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 23; 2022: 16; 2023: 15; 2024: 12; 2025: 2; 2026: 1.

69 papers.

Sort:

By area:

  1. 2021iMAP: Implicit Mapping and Positioning in Real-Timecited by 476
  2. 2022CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learningcited by 446
  3. 2021DyTox: Transformers for Continual Learning with DYnamic TOken eXpansioncited by 291
  4. 2021Online Continual Learning in Image Classification: An Empirical Surveycited by 242
  5. 2022FOSTER: Feature Boosting and Compression for Class-Incremental Learningcited by 228
  6. 2023Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Modelscited by 175
  7. 2023Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRAcited by 138
  8. 2023Continual Pre-Training of Large Language Models: How to (re)warm your model?cited by 135
  9. 2021Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learningcited by 130
  10. 2024Continual Learning and Catastrophic Forgettingcited by 73
  11. 2021Replay in Deep Learning: Current Approaches and Missing Biological Elementscited by 71
  12. 2021Continual Learning via Local Module Compositioncited by 61
38 more
  1. 2024Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuningcited by 59
  2. 2021Recent Advances of Continual Learning in Computer Vision: An Overviewcited by 55
  3. 2022A Closer Look at Rehearsal-Free Continual Learningcited by 54
  4. 2022PIVOT: Prompting for Video Continual Learningcited by 45
  5. 2023A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Taskscited by 41
  6. 2021Class-Incremental Learning with Generative Classifierscited by 39
  7. 2021Understanding Continual Learning Settings with Data Distribution Drift Analysiscited by 38
  8. 2021Curriculum-Meta Learning for Order-Robust Continual Relation Extractioncited by 34
  9. 2021Continuum: Simple Management of Complex Continual Learning Scenarioscited by 33
  10. 2021CLEVA-Compass: A Continual Learning EValuation Assessment Compass to Promote Research Transparency and Comparabilitycited by 28
  11. 2021Optimizing Reusable Knowledge for Continual Learning via Metalearningcited by 24
  12. 2021CRIL: Continual Robot Imitation Learning via Generative and Prediction Modelcited by 23
  13. 2021Sequoia: A Software Framework to Unify Continual Learning Researchcited by 19
  14. 2021Continual Learning in Deep Networks: an Analysis of the Last Layercited by 17
  15. 2024Text-Enhanced Data-free Approach for Federated Class-Incremental Learningcited by 16
  16. 2023Exploring Continual Learning of Diffusion Modelscited by 15
  17. 2021Do Not Forget to Attend to Uncertainty while Mitigating Catastrophic Forgettingcited by 12
  18. 2023When Meta-Learning Meets Online and Continual Learning: A Surveycited by 12
  19. 2022Beyond Supervised Continual Learning: a Reviewcited by 11
  20. 2023Continual Learning for Predictive Maintenance: Overview and Challengescited by 10
  21. 2023Just a Glimpse: Rethinking Temporal Information for Video Continual Learningcited by 10
  22. 2024M2Distill: Multi-Modal Distillation for Lifelong Imitation Learningcited by 10
  23. 2022Memory Population in Continual Learning via Outlier Eliminationcited by 9
  24. 2022Continual Learning Approaches for Anomaly Detectioncited by 9
  25. 2022Entropy-based Stability-Plasticity for Lifelong Learningcited by 8
  26. 2022A Benchmark and Empirical Analysis for Replay Strategies in Continual Learningcited by 8
  27. 2021Overcoming Catastrophic Forgetting with Gaussian Mixture Replaycited by 7
  28. 2022False Memory Formation in Continual Learners Through Imperceptible Backdoor Triggercited by 6
  29. 2023Model Inversion Attack via Dynamic Memory Learningcited by 6
  30. 2023Adaptive Visual Scene Understanding: Incremental Scene Graph Generationcited by 6
  31. 2024Joint Diffusion models in Continual Learningcited by 6
  32. 2021Multiband VAE: Latent Space Alignment for Knowledge Consolidation in Continual Learningcited by 5
  33. 2022Self-Activating Neural Ensembles for Continual Reinforcement Learningcited by 5
  34. 2024Coherent Temporal Synthesis for Incremental Action Segmentationcited by 5
  35. 2024Federated Continual Learning Goes Online: Uncertainty-Aware Memory Management for Vision Tasks and Beyondcited by 5
  36. 2021A Procedural World Generation Framework for Systematic Evaluation of Continual Learningcited by 4
  37. 2021Memory-Free Generative Replay For Class-Incremental Learningcited by 4
  38. 2022Generative Negative Replay for Continual Learningcited by 4

50 most cited of 69 All 69 (JSON)