mlsanityData to 14 Oct 2026

Few-shot Class-incremental Learning for Classification and Object Detection: A Survey

arXiv 2308.06764 ↗First posted 13 Aug 2023cs.LG cs.AIcited by 25

Not on the map. Why?

Abstract (arXiv)

Few-shot Class-Incremental Learning (FSCIL) presents a unique challenge in Machine Learning (ML), as it necessitates the Incremental Learning (IL) of new classes from sparsely labeled training samples without forgetting previous knowledge. While this field has seen recent progress, it remains an active exploration area. This paper aims to provide a comprehensive and systematic review of FSCIL. In our in-depth examination, we delve into various facets of FSCIL, encompassing the problem definition, the discussion of the primary challenges of unreliable empirical risk minimization and the stability-plasticity dilemma, general schemes, and relevant problems of IL and Few-shot Learning (FSL). Besides, we offer an overview of benchmark datasets and evaluation metrics. Furthermore, we introduce the Few-shot Class-incremental Classification (FSCIC) methods from data-based, structure-based, and optimization-based approaches and the Few-shot Class-incremental Object Detection (FSCIOD) methods from anchor-free and anchor-based approaches. Beyond these, we present several promising research directions within FSCIL that merit further investigation.

Key facts. Cited by 25 papers in the map (data through 14 Oct 2026). Builds on 48 of its 104 references that are in the map. First posted on arXiv 13 Aug 2023.

Builds on

48 of 104 references.

References · 48

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  6. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  7. 2020End-to-End Object Detection with Transformerscited by 7,414
  8. 2017Mask R-CNNcited by 7,277
  9. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  10. 2016Matching Networks for One Shot Learningcited by 2,255
  11. 2020Knowledge Distillation: A Surveycited by 1,603
  12. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
36 more
  1. 2019Objects as Pointscited by 1,175
  2. 2016Optimization Methods for Large-Scale Machine Learningcited by 1,150
  3. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  4. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 898
  5. 2020Prevalence of Neural Collapse during the terminal phase of deep learning trainingcited by 719
  6. 2019A Closer Look at Few-shot Classificationcited by 684
  7. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 540
  8. 2020Class-incremental learning: survey and performance evaluation on image classificationcited by 449
  9. 2020Few-Shot Class-Incremental Learningcited by 251
  10. 2021Online Continual Learning in Image Classification: An Empirical Surveycited by 245
  11. 2020Semantic Drift Compensation for Class-Incremental Learningcited by 241
  12. 2023Class-Incremental Learning: A Surveycited by 209
  13. 2018Towards Robust Evaluations of Continual Learningcited by 148
  14. 2016An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wildcited by 146
  15. 2021Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minimacited by 118
  16. 2021Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learningcited by 115
  17. 2018Continuous Learning in Single-Incremental-Task Scenarioscited by 109
  18. 2020A Comprehensive Study of Class Incremental Learning Algorithms for Visual Taskscited by 107
  19. 2021Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learningcited by 96
  20. 2022Constrained Few-shot Class-incremental Learningcited by 94
  21. 2022Few-Shot Class-Incremental Learning by Sampling Multi-Phase Taskscited by 88
  22. 2022Few-Shot Class-Incremental Learning from an Open-Set Perspectivecited by 84
  23. 2022Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replaycited by 72
  24. 2021Few-Shot Lifelong Learningcited by 59
  25. 2023Learning with Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learningcited by 55
  26. 2021Incremental Few-Shot Instance Segmentationcited by 49
  27. 2022Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigationcited by 45
  28. 2020The Devil is in the Details: Self-Supervised Attention for Vehicle Re-Identificationcited by 39
  29. 2021Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgettingcited by 33
  30. 2022Memorizing Complementation Network for Few-Shot Class-Incremental Learningcited by 30
  31. 2022Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detectioncited by 23
  32. 2023S3C: Self-Supervised Stochastic Classifiers for Few-Shot Class-Incremental Learningcited by 23
  33. 2022iFS-RCNN: An Incremental Few-shot Instance Segmentercited by 19
  34. 2023Uncertainty-Aware Distillation for Semi-Supervised Few-Shot Class-Incremental Learningcited by 16
  35. 2022Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learningcited by 14
  36. 2021Learnable Expansion-and-Compression Network for Few-shot Class-Incremental Learningcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 4; 2025: 15; 2026: 5.

25 papers.

Sort:

By area:

  1. 2024MAGR: Manifold-Aligned Graph Regularization for Continual Action Quality Assessmentcited by 13
  2. 2025Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detectioncited by 8
  3. 2024Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learningcited by 7
  4. 2025Generalized Incremental Learning under Concept Drift across Evolving Data Streamscited by 7
  5. 2025RICO: Two Realistic Benchmarks and an In-Depth Analysis for Incremental Learning in Object Detectioncited by 5
  6. 2023FAGC:Feature Augmentation on Geodesic Curve in the Pre-Shape Spacecited by 4
  7. 2024Beyond Few-shot Object Detection: A Detailed Surveycited by 2
  8. 2024TiROD: Tiny Robotics Dataset and Benchmark for Continual Object Detectioncited by 2
  9. 2025ISP-AD: A Large-Scale Real-World Dataset for Advancing Industrial Anomaly Detection with Synthetic and Real Defectscited by 2
  10. 2025Incomplete In-context Learningcited by 2
  11. 2025Few-Shot Learning in Video and 3D Object Detection: A Surveycited by 2
  12. 2025DSS-Prompt: Dynamic-Static Synergistic Prompting for Few-Shot Class-Incremental Learningcited by 2
13 more
  1. 2025Incremental Object Detection with Prompt-based Methodscited by 2
  2. 2026Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuningcited by 2
  3. 2025Does Prior Data Matter? Exploring Joint Training in the Context of Few-Shot Class-Incremental Learningcited by 1
  4. 2025Consistency-Driven Calibration and Matching for Few-Shot Class-Incremental Learningcited by 1
  5. 2025Brain-inspired analogical mixture prototypes for few-shot class-incremental learningcited by 0
  6. 2025From Dataset to Real-world: General 3D Object Detection via Generalized Cross-domain Few-shot Learningcited by 0
  7. 2025Cross-Domain Attribute Alignment with CLIP: A Rehearsal-Free Approach for Class-Incremental Unsupervised Domain Adaptationcited by 0
  8. 2025SAFA-SNN: Sparsity-Aware On-Device Few-Shot Class-Incremental Learning with Fast-Adaptive Structure of Spiking Neural Networkcited by 0
  9. 2025Improving Sustainability of Adversarial Examples in Class-Incremental Learningcited by 0
  10. 2026From Selection to Scheduling: Federated Geometry-Aware Correction Makes Exemplar Replay Work Better under Continual Dynamic Heterogeneitycited by 0
  11. 2026Quantum Incremental Learning with Mixed State Prototypescited by 0
  12. 2026Socialized Division and Collaboration: Rethinking Class-Incremental Learning under Optimization Conflictscited by 0
  13. 2026A Kernel-Based Modular Discriminant Analysis Framework for Small-Sample Learningcited by 0