Data to 7 Oct 2026

Few-Shot Class-Incremental Learning

arXiv 2004.10956 ↗First posted 23 Apr 2020cs.CV cs.LG stat.MLcited by 249

Not on the map. Why?

Abstract (arXiv)

The ability to incrementally learn new classes is crucial to the development of real-world artificial intelligence systems. In this paper, we focus on a challenging but practical few-shot class-incremental learning (FSCIL) problem. FSCIL requires CNN models to incrementally learn new classes from very few labelled samples, without forgetting the previously learned ones. To address this problem, we represent the knowledge using a neural gas (NG) network, which can learn and preserve the topology of the feature manifold formed by different classes. On this basis, we propose the TOpology-Preserving knowledge InCrementer (TOPIC) framework. TOPIC mitigates the forgetting of the old classes by stabilizing NG's topology and improves the representation learning for few-shot new classes by growing and adapting NG to new training samples. Comprehensive experimental results demonstrate that our proposed method significantly outperforms other state-of-the-art class-incremental learning methods on CIFAR100, miniImageNet, and CUB200 datasets.

Key facts. Cited by 249 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 26; 2022: 40; 2023: 60; 2024: 58; 2025: 42; 2026: 23.

249 papers.

Sort:

By area:

2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
2023Class-Incremental Learning: A Surveycited by 209
2021Few-Shot Incremental Learning with Continually Evolved Classifierscited by 184
2023Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Needcited by 183
2022Forward Compatible Few-Shot Class-Incremental Learningcited by 125
2021Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minimacited by 118
2021Distilling Causal Effect of Data in Class-Incremental Learningcited by 117
2021Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learningcited by 114
2023Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learningcited by 112
2021Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learningcited by 95
2022"This is my unicorn, Fluffy": Personalizing frozen vision-language representationscited by 95
2022Constrained Few-shot Class-incremental Learningcited by 93

38 more

2022Few-Shot Class-Incremental Learning by Sampling Multi-Phase Taskscited by 87
2023FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learningcited by 86
2022Few-Shot Class-Incremental Learning from an Open-Set Perspectivecited by 83
2022Continual Learning of Natural Language Processing Tasks: A Surveycited by 83
2022Memory Replay with Data Compression for Continual Learningcited by 80
2022Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replaycited by 70
2021ORDisCo: Effective and Efficient Usage of Incremental Unlabeled Data for Semi-supervised Continual Learningcited by 68
2023A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learningcited by 66
2021Few-Shot Lifelong Learningcited by 58
2021Recent Advances of Continual Learning in Computer Vision: An Overviewcited by 55
2023Learning with Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learningcited by 55
2021Subspace Regularizers for Few-Shot Class Incremental Learningcited by 54
2024Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Modelscited by 54
2021Self-Supervised Training Enhances Online Continual Learningcited by 53
2021Shallow Bayesian Meta Learning for Real-World Few-Shot Recognitioncited by 48
2022Online Continual Learning for Embedded Devicescited by 48
2023A Survey on Few-Shot Class-Incremental Learningcited by 48
2023First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learningcited by 46
2022Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigationcited by 45
2022Isolation and Impartial Aggregation: A Paradigm of Incremental Learning without Interferencecited by 44
2023Few-Shot Class-Incremental Learning via Training-Free Prototype Calibrationcited by 44
2021Graph Few-shot Class-incremental Learningcited by 40
2021Co-Transport for Class-Incremental Learningcited by 38
2022On the Soft-Subnetwork for Few-shot Class Incremental Learningcited by 37
2022Long-Tailed Class Incremental Learningcited by 36
2024Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learnerscited by 35
2021Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgettingcited by 33
2022Memorizing Complementation Network for Few-Shot Class-Incremental Learningcited by 30
2022Learning with Recoverable Forgettingcited by 29
2023NeuroBench: A Framework for Benchmarking Neuromorphic Computing Algorithms and Systemscited by 27
2021GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learningcited by 26
2023Few-shot Class-incremental Learning for Classification and Object Detection: A Surveycited by 25
2024OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learningcited by 25
2022Few-Shot Continual Active Learning by a Robotcited by 24
2022Doodle It Yourself: Class Incremental Learning by Drawing a Few Sketchescited by 23
2023S3C: Self-Supervised Stochastic Classifiers for Few-Shot Class-Incremental Learningcited by 23
2024Generative Multi-modal Models are Good Class-Incremental Learnerscited by 22
2022Geometer: Graph Few-Shot Class-Incremental Learning via Prototype Representationcited by 21

50 most cited of 249 All 249 (JSON)