mlsanityData to 7 Oct 2026

Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgetting

arXiv 2108.08165 ↗First posted 18 Aug 2021cs.CVcited by 33

Not on the map. Why?

Abstract (arXiv)

Both generalized and incremental few-shot learning have to deal with three major challenges: learning novel classes from only few samples per class, preventing catastrophic forgetting of base classes, and classifier calibration across novel and base classes. In this work we propose a three-stage framework that allows to explicitly and effectively address these challenges. While the first phase learns base classes with many samples, the second phase learns a calibrated classifier for novel classes from few samples while also preventing catastrophic forgetting. In the final phase, calibration is achieved across all classes. We evaluate the proposed framework on four challenging benchmark datasets for image and video few-shot classification and obtain state-of-the-art results for both generalized and incremental few shot learning.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Builds on 35 of its 56 references that are in the map. First posted on arXiv 18 Aug 2021.

Builds on

35 of 56 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2016Learning without Forgettingcited by 2,465
  7. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  8. 2016Matching Networks for One Shot Learningcited by 2,246
  9. 2017The Kinetics Human Action Video Datasetcited by 1,894
  10. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  11. 2019Large Scale Incremental Learningcited by 727
  12. 2018End-to-End Incremental Learningcited by 596
23 more
  1. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  2. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
  3. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  4. 2019Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLcited by 359
  5. 2019A Baseline for Few-Shot Image Classificationcited by 298
  6. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
  7. 2018DropBlock: A regularization method for convolutional networkscited by 261
  8. 2020Few-Shot Class-Incremental Learningcited by 249
  9. 2020Semantic Drift Compensation for Class-Incremental Learningcited by 241
  10. 2020Mnemonics Training: Multi-Class Incremental Learning without Forgettingcited by 220
  11. 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
  12. 2018Low-Shot Learning from Imaginary Datacited by 181
  13. 2020SS-IL: Separated Softmax for Incremental Learningcited by 126
  14. 2019Overcoming Catastrophic Forgetting with Unlabeled Data in the Wildcited by 111
  15. 2020iTAML: An Incremental Task-Agnostic Meta-learning Approachcited by 90
  16. 2019Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learningcited by 69
  17. 2018Incremental Few-Shot Learning with Attention Attractor Networkscited by 65
  18. 2021Essentials for Class Incremental Learningcited by 57
  19. 2020ScaIL: Classifier Weights Scaling for Class Incremental Learningcited by 47
  20. 2019Few-Shot Learning with Global Class Representationscited by 44
  21. 2019ProtoGAN: Towards Few Shot Learning for Action Recognitioncited by 41
  22. 2020Continual Representation Learning for Biometric Identificationcited by 25
  23. 2019Relational Generalized Few-Shot Learningcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 4; 2023: 11; 2024: 7; 2025: 6; 2026: 3.

33 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  2. 2022Forward Compatible Few-Shot Class-Incremental Learningcited by 125
  3. 2023RMM: Reinforced Memory Management for Class-Incremental Learningcited by 66
  4. 2023A Survey on Few-Shot Class-Incremental Learningcited by 48
  5. 2023Few-Shot Class-Incremental Learning via Training-Free Prototype Calibrationcited by 44
  6. 2023Few-shot Class-incremental Learning for Classification and Object Detection: A Surveycited by 25
  7. 2024OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learningcited by 25
  8. 2024Few-Shot Class Incremental Learning with Attention-Aware Self-Adaptive Promptcited by 15
  9. 2024Learning Prompt with Distribution-Based Feature Replay for Few-Shot Class-Incremental Learningcited by 12
  10. 2021Coarse-To-Fine Incremental Few-Shot Learningcited by 9
  11. 2025Revisiting Pool-based Prompt Learning for Few-shot Class-incremental Learningcited by 8
  12. 2023Generalized Few-Shot 3D Object Detection of LiDAR Point Cloud for Autonomous Drivingcited by 6
21 more
  1. 2023Semantic-visual Guided Transformer for Few-shot Class-incremental Learningcited by 6
  2. 2023Decomposed Prototype Learning for Few-Shot Scene Graph Generationcited by 4
  3. 2024Enhanced Few-Shot Class-Incremental Learning via Ensemble Modelscited by 4
  4. 2022Better Generalized Few-Shot Learning Even Without Base Datacited by 3
  5. 2024Class Balance Matters to Active Class-Incremental Learningcited by 3
  6. 2022Incremental Few-Shot Learning via Implanting and Compressingcited by 2
  7. 2024Inductive Graph Few-shot Class Incremental Learningcited by 2
  8. 2021A Strong Baseline for Semi-Supervised Incremental Few-Shot Learningcited by 1
  9. 2023Generalized Cross-domain Multi-label Few-shot Learning for Chest X-rayscited by 1
  10. 2025Continuous Knowledge-Preserving Decomposition with Adaptive Layer Selection for Few-Shot Class-Incremental Learningcited by 1
  11. 2025Consistency-Driven Calibration and Matching for Few-Shot Class-Incremental Learningcited by 1
  12. 2022Expanding continual few-shot learning benchmarks to include recognition of specific instancescited by 0
  13. 2023A Forward and Backward Compatible Framework for Few-shot Class-incremental Pill Recognitioncited by 0
  14. 2023Aggregated f-average Neural Network applied to Few-Shot Class Incremental Learningcited by 0
  15. 2024Continual Gesture Learning without Data via Synthetic Feature Samplingcited by 0
  16. 2025Brain-inspired analogical mixture prototypes for few-shot class-incremental learningcited by 0
  17. 2025Sculpting Margin Penalty: Intra-Task Adapter Merging and Classifier Calibration for Few-Shot Class-Incremental Learningcited by 0
  18. 2025MoTiC: Momentum Tightness and Contrast for Few-Shot Class-Incremental Learningcited by 0
  19. 2026CD^2: Constrained Dataset Distillation for Few-Shot Class-Incremental Learningcited by 0
  20. 2026Optical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learningcited by 0
  21. 2026Decompose, Compare, and Decide: Multimodal LLMs are Implicit Few-Shot Learnerscited by 0