mlsanityData to 7 Oct 2026

Encoder Based Lifelong Learning

arXiv 1704.01920 ↗First posted 6 Apr 2017cs.CV cs.AI stat.MLcited by 102

Not on the map. Why?

Abstract (arXiv)

This paper introduces a new lifelong learning solution where a single model is trained for a sequence of tasks. The main challenge that vision systems face in this context is catastrophic forgetting: as they tend to adapt to the most recently seen task, they lose performance on the tasks that were learned previously. Our method aims at preserving the knowledge of the previous tasks while learning a new one by using autoencoders. For each task, an under-complete autoencoder is learned, capturing the features that are crucial for its achievement. When a new task is presented to the system, we prevent the reconstructions of the features with these autoencoders from changing, which has the effect of preserving the information on which the previous tasks are mainly relying. At the same time, the features are given space to adjust to the most recent environment as only their projection into a low dimension submanifold is controlled. The proposed system is evaluated on image classification tasks and shows a reduction of forgetting over the state-of-the-art

Key facts. Cited by 102 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 26; 2022: 20; 2023: 24; 2024: 17; 2025: 11; 2026: 4.

102 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  2. 2021Online Continual Learning in Image Classification: An Empirical Surveycited by 242
  3. 2023Class-Incremental Learning: A Surveycited by 209
  4. 2025RL's Razor: Why Online Reinforcement Learning Forgets Lesscited by 162
  5. 2021Supervised Contrastive Replay: Revisiting the Nearest Class Mean Classifier in Online Class-Incremental Continual Learningcited by 140
  6. 2021Continual Learning for Text Classification with Information Disentanglement Based Regularizationcited by 86
  7. 2021Recent Advances of Continual Learning in Computer Vision: An Overviewcited by 55
  8. 2022Continual evaluation for lifelong learning: Identifying the stability gapcited by 55
  9. 2022An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditionscited by 54
  10. 2023Dense Network Expansion for Class Incremental Learningcited by 45
  11. 2023LM-Cocktail: Resilient Tuning of Language Models via Model Mergingcited by 44
  12. 2023Traj-MAE: Masked Autoencoders for Trajectory Predictioncited by 42
38 more
  1. 2021Graph Few-shot Class-incremental Learningcited by 40
  2. 2021Continual Learning for Blind Image Quality Assessmentcited by 36
  3. 2021Multi-View Correlation Distillation for Incremental Object Detectioncited by 36
  4. 2022The Challenges of Continuous Self-Supervised Learningcited by 36
  5. 2023Online Hyperparameter Optimization for Class-Incremental Learningcited by 36
  6. 2021Towards Better Plasticity-Stability Trade-off in Incremental Learning: A Simple Linear Connectorcited by 34
  7. 2021Continual Neural Mapping: Learning An Implicit Scene Representation from Sequential Observationscited by 30
  8. 2022Open-world Semantic Segmentation for LIDAR Point Cloudscited by 29
  9. 2022Balancing Stability and Plasticity through Advanced Null Space in Continual Learningcited by 29
  10. 2022Mining Unseen Classes via Regional Objectness: A Simple Baseline for Incremental Segmentationcited by 28
  11. 2023Lossless Adaptation of Pretrained Vision Models For Robotic Manipulationcited by 28
  12. 2023Diversifying the Mixture-of-Experts Representation for Language Models with Orthogonal Optimizercited by 28
  13. 2022Reinforced Continual Learning for Graphscited by 24
  14. 2023Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomycited by 24
  15. 2023Continual Learning in Medical Image Analysis: A Comprehensive Review of Recent Advancements and Future Prospectscited by 22
  16. 2022Continual Learning Based on OOD Detection and Task Maskingcited by 21
  17. 2022Online Continual Learning with Contrastive Vision Transformercited by 21
  18. 2021On the importance of cross-task features for class-incremental learningcited by 18
  19. 2023Rethinking Momentum Knowledge Distillation in Online Continual Learningcited by 18
  20. 2023CoinSeg: Contrast Inter- and Intra- Class Representations for Incremental Segmentationcited by 18
  21. 2021Improving Vision Transformers for Incremental Learningcited by 17
  22. 2022Continual Learning for Visual Search with Backward Consistent Feature Embeddingcited by 17
  23. 2023Continual Graph Learning: A Surveycited by 17
  24. 2021Cognitively Inspired Learning of Incremental Drifting Conceptscited by 16
  25. 2022Sparse Coding in a Dual Memory System for Lifelong Learningcited by 16
  26. 2025Upweighting Easy Samples in Fine-Tuning Mitigates Forgettingcited by 16
  27. 2021Lifelong Learning with Sketched Structural Regularizationcited by 15
  28. 2021In Defense of the Learning Without Forgetting for Task Incremental Learningcited by 13
  29. 2024MoFO: Momentum-Filtered Optimizer for Mitigating Forgetting in LLM Fine-Tuningcited by 13
  30. 2024Open World Object Detection: A Surveycited by 13
  31. 2021Do Not Forget to Attend to Uncertainty while Mitigating Catastrophic Forgettingcited by 12
  32. 2021AirLoop: Lifelong Loop Closure Detectioncited by 11
  33. 2024Continual Learning on Graphs: A Surveycited by 11
  34. 2025ProtoDepth: Unsupervised Continual Depth Completion with Prototypescited by 11
  35. 2025Parameter-Efficient Continual Fine-Tuning: A Surveycited by 11
  36. 2021Continual learning in cross-modal retrievalcited by 10
  37. 2023Continual Learning for Predictive Maintenance: Overview and Challengescited by 10
  38. 2023Preventing Catastrophic Forgetting in Continual Learning of New Natural Language Taskscited by 10

50 most cited of 102 All 102 (JSON)