The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Semi-Supervised Few-Shot Class-Incremental Learning
Abstract
The capability of incrementally learning new classes and learning from a few examples is one of the hallmarks of human intelligence. It is crucial to endow a practical recognition system with such ability. Therefore, in this paper, we conduct pioneering work and focus on a challenging yet practical Semi-Supervised Few-Shot Class-Incremental Learning (SSFSCIL) problem, which requires CNN models incrementally learn new classes from very few labeled samples and a large number of unlabeled samples, without forgetting the previously learned ones. To address this problem, a simple and efficient solution for SSFSCIL is proposed to learn novel categories using a self-training strategy in a semi-supervised manner and avoid catastrophic forgetting by distillation-based methods. Our extensive experiments on CIFAR100, mini ImageNet and CUB200 datasets demonstrate the promising performance of our proposed method, and define baselines in this new research direction.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Cui et al. [93] leveraged them to propose semi-supervised FSCIL.”
From Few-Shot Class-Incremental Learning for Classification and Object Detection: A Survey (2025) · cites this paper as [93]
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
nuScenes: A Multimodal Dataset for Autonomous Driving
Caesar, H., Bankiti, V., Lang, A. H., Vora, S., Liong, V. E., Xu, Q., Krishnan, A., Pan, Y., Baldan, G., & Beijbom, O. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01164 · Cited by 7,152
Memory Aware Synapses: Learning What (not) to Forget
Aljundi, R., Babiloni, F., Elhoseiny, M., Rohrbach, M., & Tuytelaars, T. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01219-9_9 · Cited by 1,590
Research works printed but not linked: 22
- vinyals, 2016, Matching networks for one shot learning, NeurIPS
- 10.1109/CVPR42600.2020.01287 · DOI
- 10.1109/CVPR.2018.00131 · DOI
- 10.1109/TPAMI.2017.2773081 · DOI · Paper page
- 10.1007/978-3-030-01258-8_15 · DOI · Paper page
- 10.1109/CVPR.2019.00092 · DOI · Paper page
- 10.1109/CVPR.2017.587 · DOI · Paper page
- zenke, 2017, Continual learning through synaptic intelligence, Machine Learning Research, 70, 3987
- 10.1007/978-3-319-65981-7_12 · DOI
- 10.1146/annurev-bioeng-071516-044442 · DOI · Paper page
- 10.1145/2492385.2492390 · DOI
- finn, 2017, Model-agnostic meta-learning for fast adaptation of deep networks, ICML
- maurer, 2016, Autonomous Driving Technical Legal and Social Aspects
- 10.1007/s11263-019-01191-3 · DOI
- hsu, 2019, Unsupervised learning via meta-learning, ICLRE
- 10.1109/CVPR42600.2020.01220 · DOI · Paper page
- 10.1109/TIT.1965.1053799 · DOI
- krizhevsky, 2009, Learning multiple layers of features from tiny images
- 10.1109/ACVMOT.2005.107 · DOI · Paper page
- hinton, 2014, Dis-tilling the knowledge in a neural network, NeurIPS 3D Deep Learning Workshop
- chaudhry, 2018, Efficient lifelong learning with a-gem, arXiv preprint arXiv 1812 11720
- 10.1214/aoms/1177729586 · DOI · Paper page
Cited by
Sorted by citations
Few-Shot Class-Incremental Learning for Classification and Object Detection: A Survey
Zhang, J., Liu, L., Silvén, O., Pietikäinen, M., & Hu, D. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3529038 · Cited by 84
“In the context of FSCIL, Cui et al. proposed a series of semi-supervised methods that leverage KD and unlabeled data [45], [46], [93].”
Self-citation
Metadata
- Authors
- Cui, Y., Xiong, W., Tavakolian, M., & Liu, L.
- Affiliations
- University of Oulu (FI)
- National University of Defense Technology (CN)
- Venue
- 2021 IEEE International Conference on Image Processing (ICIP)
- Publisher
- IEEE
- Published
- 2021-09-19
- Pages
- 1239-1243
- ISSN
- 1522-4880 (ISSN-L)
- OpenAlex
- W3195897026
- Cited by
- 16
- References
- 3
- Citations by year
- 2026: 1 · 2025: 4 · 2024: 5 · 2023: 3 · 2022: 3
- FWCI
- 1.27
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Proceedings - International Conference on Image Processing (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Algorithms
- Keywords
- semi-supervised learning, few-shot learning, class-incremental learning, catastrophic forgetting, self-training, knowledge distillation, convolutional neural networks, novel category recognition, unlabeled samples
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
