mlsanityData to 14 Oct 2026

Few-Shot Continual Learning via Flat-to-Wide Approaches

arXiv 2306.14369 ↗First posted 26 Jun 2023cs.LG cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Existing approaches on continual learning call for a lot of samples in their training processes. Such approaches are impractical for many real-world problems having limited samples because of the overfitting problem. This paper proposes a few-shot continual learning approach, termed FLat-tO-WidE AppRoach (FLOWER), where a flat-to-wide learning process finding the flat-wide minima is proposed to address the catastrophic forgetting problem. The issue of data scarcity is overcome with a data augmentation approach making use of a ball generator concept to restrict the sampling space into the smallest enclosing ball. Our numerical studies demonstrate the advantage of FLOWER achieving significantly improved performances over prior arts notably in the small base tasks. For further study, source codes of FLOWER, competitor algorithms and experimental logs are shared publicly in urlhttps://github.com/anwarmaxsum/FLOWER.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 31 of its 40 references that are in the map. First posted on arXiv 26 Jun 2023.

Builds on

31 of 40 references.

References · 31

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  2. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  4. 2016Learning without Forgettingcited by 2,496
  5. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  6. 2017Gradient Episodic Memory for Continual Learningcited by 1,898
  7. 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
  8. 2016Progressive Neural Networkscited by 1,361
  9. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,330
  10. 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,105
  11. 2018Efficient Lifelong Learning with A-GEMcited by 1,058
  12. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 911
19 more
  1. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 809
  2. 2017Lifelong Learning with Dynamically Expandable Networkscited by 694
  3. 2019Three scenarios for continual learningcited by 614
  4. 2018End-to-End Incremental Learningcited by 597
  5. 2019Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgettingcited by 302
  6. 2020Few-Shot Class-Incremental Learningcited by 251
  7. 2021Few-Shot Incremental Learning with Continually Evolved Classifierscited by 187
  8. 2020Using Hindsight to Anchor Past Knowledge in Continual Learningcited by 161
  9. 2022Forward Compatible Few-Shot Class-Incremental Learningcited by 127
  10. 2021Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minimacited by 118
  11. 2020CPR: Classifier-Projection Regularization for Continual Learningcited by 62
  12. 2021Few-Shot Lifelong Learningcited by 59
  13. 2019Overcoming Catastrophic Forgetting by Neuron-level Plasticity Controlcited by 36
  14. 2022Reinforced Continual Learning for Graphscited by 24
  15. 2021Unsupervised Continual Learning via Self-Adaptive Deep Clustering Approachcited by 19
  16. 2021Unsupervised Continual Learning in Streaming Environmentscited by 19
  17. 2021Continual Learning via Inter-Task Synaptic Mappingcited by 14
  18. 2022Class-Incremental Learning via Knowledge Amalgamationcited by 9
  19. 2022Scalable Adversarial Online Continual Learningcited by 6

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 2.

4 papers.

  1. 2024Few-Shot Class Incremental Learning via Robust Transformer Approachcited by 4
  2. 2025Latest Advancements Towards Catastrophic Forgetting under Data Scarcity: A Comprehensive Survey on Few-Shot Class Incremental Learningcited by 4
  3. 2025Continual Knowledge Consolidation LORA for Domain Incremental Learningcited by 2
  4. 2024Unsupervised Few-Shot Continual Learning for Remote Sensing Image Scene Classificationcited by 1