mlsanityData to 14 Oct 2026

Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning

arXiv 1904.03137 ↗First posted 5 Apr 2019cs.NE cs.CV cs.LGcited by 182

Not on the map. Why?

Abstract (arXiv)

Models trained in the context of continual learning (CL) should be able to learn from a stream of data over an undefined period of time. The main challenges herein are: 1) maintaining old knowledge while simultaneously benefiting from it when learning new tasks, and 2) guaranteeing model scalability with a growing amount of data to learn from. In order to tackle these challenges, we introduce Dynamic Generative Memory (DGM) - a synaptic plasticity driven framework for continual learning. DGM relies on conditional generative adversarial networks with learnable connection plasticity realized with neural masking. Specifically, we evaluate two variants of neural masking: applied to (i) layer activations and (ii) to connection weights directly. Furthermore, we propose a dynamic network expansion mechanism that ensures sufficient model capacity to accommodate for continually incoming tasks. The amount of added capacity is determined dynamically from the learned binary mask. We evaluate DGM in the continual class-incremental setup on visual classification tasks.

Key facts. Cited by 182 papers in the map (data through 14 Oct 2026). First posted on arXiv 5 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 33; 2022: 40; 2023: 39; 2024: 32; 2025: 26; 2026: 12.

182 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 872
  2. 2022CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learningcited by 450
  3. 2021DER: Dynamically Expandable Representation for Class Incremental Learningcited by 355
  4. 2021Online Continual Learning in Image Classification: An Empirical Surveycited by 245
  5. 2023Class-Incremental Learning: A Surveycited by 209
  6. 2023Understanding plasticity in neural networkscited by 174
  7. 2021Self-Supervised Models are Continual Learnerscited by 149
  8. 2021Training Networks in Null Space of Feature Covariance for Continual Learningcited by 143
  9. 2023Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRAcited by 141
  10. 2021Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learningcited by 131
  11. 2024Simple and Scalable Strategies to Continually Pre-train Large Language Modelscited by 127
  12. 2022Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidationcited by 113
38 more
  1. 2021Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representationscited by 96
  2. 2021RECALL: Replay-based Continual Learning in Semantic Segmentationcited by 83
  3. 2022A Theoretical Study on Solving Continual Learningcited by 80
  4. 2023Learning without Forgetting for Vision-Language Modelscited by 79
  5. 2021Replay in Deep Learning: Current Approaches and Missing Biological Elementscited by 72
  6. 2021ORDisCo: Effective and Efficient Usage of Incremental Unlabeled Data for Semi-supervised Continual Learningcited by 68
  7. 2021Continual Learning via Local Module Compositioncited by 63
  8. 2021Recent Advances of Continual Learning in Computer Vision: An Overviewcited by 55
  9. 2022A Closer Look at Rehearsal-Free Continual Learningcited by 54
  10. 2022Online Continual Learning for Embedded Devicescited by 49
  11. 2021Understanding Catastrophic Forgetting and Remembering in Continual Learning with Optimal Relevance Mappingcited by 48
  12. 2022Class-Incremental Learning for Action Recognition in Videoscited by 46
  13. 2021EEC: Learning to Encode and Regenerate Images for Continual Learningcited by 40
  14. 2022Uncertainty-aware Contrastive Distillation for Incremental Semantic Segmentationcited by 37
  15. 2023Audio-Visual Class-Incremental Learningcited by 33
  16. 2025SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction Tuningcited by 33
  17. 2022vCLIMB: A Novel Video Class Incremental Learning Benchmarkcited by 28
  18. 2022LifeLonger: A Benchmark for Continual Disease Classificationcited by 28
  19. 2023Learnability and Algorithm for Continual Learningcited by 28
  20. 2022Continual Learning with Bayesian Model based on a Fixed Pre-trained Feature Extractorcited by 27
  21. 2022A Multi-Head Model for Continual Learning via Out-of-Distribution Replaycited by 27
  22. 2021Multi-Domain Incremental Learning for Semantic Segmentationcited by 25
  23. 2022ALIFE: Adaptive Logit Regularizer and Feature Replay for Incremental Semantic Segmentationcited by 25
  24. 2023SIESTA: Efficient Online Continual Learning with Sleepcited by 24
  25. 2023Dealing with Cross-Task Class Discrimination in Online Continual Learningcited by 24
  26. 2023Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomycited by 24
  27. 2022Modeling Missing Annotations for Incremental Learning in Object Detectioncited by 23
  28. 2023Open-World Continual Learning: Unifying Novelty Detection and Continual Learningcited by 22
  29. 2021Continual Learning in Sensor-based Human Activity Recognition: an Empirical Benchmark Analysiscited by 21
  30. 2022Continual Learning Based on OOD Detection and Task Maskingcited by 21
  31. 2023Continual Segment: Towards a Single, Unified and Accessible Continual Segmentation Model of 143 Whole-body Organs in CT Scanscited by 21
  32. 2022ConStruct-VL: Data-Free Continual Structured VL Concepts Learningcited by 20
  33. 2024OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learningcited by 20
  34. 2021Preserving Earlier Knowledge in Continual Learning with the Help of All Previous Feature Extractorscited by 19
  35. 2023Continual Graph Learning: A Surveycited by 18
  36. 2023CoinSeg: Contrast Inter- and Intra- Class Representations for Incremental Segmentationcited by 18
  37. 2024SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Modelscited by 18
  38. 2024Adapter Merging with Centroid Prototype Mapping for Scalable Class-Incremental Learningcited by 18

50 most cited of 182 All 182 (JSON)