Few-Shot Class-Incremental Learning for Classification and Object Detection: A Survey
Open accessThe DOI matches its Crossref record; 123 of the 123 references it cites were found in a registry or an index; 54 of the 100 sources its claims cite were checked for support.
Abstract
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.
Overview
CoChat Summary
TL;DR
This survey systematically reviews few-shot class-incremental learning (FSCIL) for classification and object detection, covering definitions, challenges, datasets, metrics, methods, and future directions. It organizes FSCIC methods into data-, structure-, and optimization-based approaches and FSCIOD methods into anchor-free and anchor-based approaches.
Key findings
- FSCIL’s core challenges are unreliable empirical risk minimization under N-way K-shot incremental sessions and the stability-plasticity dilemma; FSCIL is a subdomain of CIL but adds scarce incremental samples and sustained unreliable risk minimization.
- For FSCIC, top base-session accuracy on mini ImageNet includes SAVC (81.12%), ALICE (80.60%), BiDistFSCIL (74.65%), TEEN (73.53%), and CLOM (73.08%); on CIFAR-100, WaRP (80.31%), BiDistFSCIL (79.45%), ALICE (79.00%), SAVC (78.77%), and TEEN (74.92%); on CUB-200, SAVC (81.85%), F2M and FSIL-GAN (81.07%), DSN (80.86%), and BiDistFSCIL (79.12%).
- Lowest performance dropping (PD) on mini ImageNet: MgSvF (17.33%), SFbFSCIL (19.14%), SPPR (19.53%), ERL++ (20.94%), and DSN (21.06%); on CIFAR-100: F2M (20.04%), SFbFSCIL (20.31%), SPPR (20.65%), TEEN (22.28%), and FACT (22.50%); on CUB-200: ALICE (17.30%), DSN (17.65%), MgSvF (17.96%), TEEN (18.13%), and BiDistFSCIL (18.19%).
- For FSCIOD, top base-class methods are Sylph, iFS-RCNN, and MCH; top novel-COCO methods are iFS-RCNN, Incremental-DETR, and iMTFA; top overall COCO methods are iFS-RCNN, Sylph, and MCH; top cross-dataset VOC methods are Incremental-DETR, BPMCH, and MCH.
Methods
- Systematic literature survey of deep FSCIL in computer vision, focused on classification and object detection; covers problem definition, core challenges, general schemes, related IL/FSL problems, benchmark datasets, evaluation metrics, method taxonomy, performance comparisons, and future directions.
- Proposes taxonomy: FSCIC methods from data-based (data replay, pseudo scenarios), structure-based (dynamic structure, attention), and optimization-based (representation learning, knowledge distillation, meta-learning, other) approaches; FSCIOD methods from anchor-free (CenterNet-, FCOS-, DETR-based) and anchor-based (Mask R-CNN) frameworks.
- Performance comparison summarizes mainstream methods on mini ImageNet, CIFAR-100, and CUB-200 for classification and COCO/VOC for detection, extracting values from original papers and noting backbones and extra factors where possible.
Limitations
- The paper states FSCIL lacks publicly available datasets and that current metrics (AA, PD; mAP, mAR, mAP50) do not fully capture detailed performance throughout continuous learning.
- It states comparisons are biased by variability in backbone networks, additional data, and implementation conditions; not all methods are open-source, and performance values are extracted from original papers.
- It states the current FSCIC setting is idealistic versus real-world needs, and FSCIOD research is insufficient, with performance far from practical application and non-unified evaluation metrics. As a survey, it presents no new experiments; this is evident from the text.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
39 Valid · 16 Not valid · 27 Not checked · 134 Own results and interpretations
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“Despite existing surveys on FSL [27, 28, 29, 30] and IL [5, 6, 7, 11, 31, 32, 33, 34, 35], there is a clear lack of systematic and comprehensive surveys specifically on FSCIL.”
What the sources say
- Not checked — no full text of the sourcecites [27] source
- Not checked — no full text of the sourcecites [28] source
- Not checked — no full text of the sourcecites [29] source
- Supportedcites [30] source
The citations in the sentence are attached to the existence of earlier FSL and IL surveys, not to the citing authors’ conclusion about a lack of FSCIL surveys. This paper identifies itself as a survey of few-shot object detection in the Introduction and reviews that field in Section 4, so it supports its use as an example of an existing survey in a few-shot learning area. It does not establish the claimed FSCIL survey gap. (LLM, conf=0.86)
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“This approach doesn't ensure strong generalization on test data, especially with limited training samples.”
What the sources say
- Not checked — no full text of the sourcecites [27] source
- Partly supportedcites [39] sourceExperimental — accuracy not yet measured
Section 8.1 says excellent generalization is difficult with very few samples, supporting the limited-data concern. The Introduction discusses minimizing empirical risk, but our copy does not specifically say that this approach fails to ensure generalization on test data. No page numbers are available in our copy. (LLM, conf=0.78)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Every source the paper cites for this claim was checked and supports it.
In the paper
“However, none of these works systematically review FSCIL.”
What the sources say
- Supportedcites [7] source
The paper identifies class-incremental learning as the subject of its survey (p. 2), and §2.3 (p. 3) narrows its evaluation to specified class-IL methods rather than few-shot class-incremental learning (FSCIL). It therefore supports the claim as applied to this cited survey, though it cannot establish the statement about every other work the citing sentence may refer to. (LLM, conf=0.84)
- Supportedcites [34] source
The Introduction describes this paper as a comprehensive survey of class-incremental learning methods, while §2.1 defines FSCIL as a distinct few-shot setting. §5 mentions a few FSCIL works as a future-direction topic rather than systematically reviewing them. The cited paper therefore supports the claim as applied to this survey; it cannot establish the scope of the other works referred to as “these works.” (LLM, conf=0.88)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“To mitigate catastrophic forgetting, some studies [44, 45, 46] use KD to maintain competent classification capabilities on previous classes while learning new ones.”
What the sources say
- Not checked — no full text of the sourcecites [44] source
- Not checked — no full text of the sourcecites [45] source
- Supportedcites [46] source
The Introduction describes UaD-CE as preserving discriminative ability on base categories while obtaining knowledge of novel categories. The Ablation Studies section explicitly says the framework uses knowledge distillation for class-incremental learning and that it helps memorize old knowledge. (LLM, conf=0.93)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Although some surveys briefly mention FSCIL [32, 35], they only provide a short introduction to the concept and a few studies without offering a thorough or systematic analysis.”
What the sources say
- Could not verifycites [32] sourceExperimental — accuracy not yet measured
The Introduction and Conclusion describe a thorough comparison of class-incremental learning algorithms, but do not characterize the paper's coverage of FSCIL. A search for “few-shot class-incremental learning” found a cited study in the References, not a passage introducing FSCIL or assessing FSCIL studies. Our copy therefore does not establish the specific claim that this survey gives FSCIL only a short introduction and a few studies. (LLM, conf=0.72)
- Supportedcites [35] source
Section 5.2, “Scarcity of Labeled Data” (page not provided), introduces FSCIL in one paragraph and briefly names representative methods. That passage supports the characterization of this survey’s FSCIL coverage as brief rather than a thorough, systematic analysis. (LLM, conf=0.88)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
56 more claims · 10 with their cited sources checked
Create a free account to see all 216 claims and to verify the 4 references still open.
- Probably not a substantial claim. 127
- It may state two separate claims as one. 74
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 2.1 Problem Definition · p. 3
“| FSCIL | 2023 | Neural Networks | A Survey on Few-Shot Class-Incremental Learning [36]”
§ REFERENCES · p. 19
“- [36] S. Tian, L. Li, W. Li, H. Ran, X. Ning, and P. Tiwari, 'A survey on fewshot class-incremental learning,' Neural Networks , vol. 169, pp. 307324, 2024.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 3.2.1 Evaluation Metrics for Classification · p. 7
“PD = A B - A 0”
§ 4.4.1 Performance Comparison · p. 14
“| SAVC [96] | CVPR 23 | 18 | 81.12 | 57.11 | 67.05 | 24.01”
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“as demonstrated by AlexNet [1] and ResNet [2], to the combined strategy of supervised pre-training and fine-tuning, with Transformer-based BERT [3] being a prime example.”
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 1×
“Therefore, this paper proposed a correction model based on Transformer [75].”
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
Exploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460 · cited 1×
“In FSCIL, the prevalent data partitioning method by Tao et al. [13] 2) Datasets for Object Detection: COCO: The Microsoft Common Objects in Context (COCO) dataset, widely used for object detection tasks, comprises 80 object classes including people, animals, vehicles, furniture, and food [61].”
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · cited 2×
“The core structure of this framework included the followingcomponents:First,featureextractorsobtainedthrough supervisedtrainingonbase-classdataandself-supervisedtasks onImageNet[58]orOpenImages-v6[87]usingmethodssuch aspretexttasks,contrastiveloss,orclustering.”
He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.322 · Cited by 29,137
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
The pascal visual object classes (VOC) challenge
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-009-0275-4 · Cited by 19,599
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58452-8_13 · Cited by 18,285 · cited 1×
“DETR-based Method: In anchor-free frameworks, in addition to the methods based on CentreNet and FCOS, another work adopts the DETR framework [107] as the backbone.”
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · arXiv · doi:10.48550/arxiv.2005.12872 · Cited by 18,253
Representation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001 · cited 1×
“1) Representation Learning-Based Methods: In FSCIL, representation learning aims to extract meaningful features from a limited stream of samples to form a “representation” of the data [76].”
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Finn, C., Abbeel, P., & Levine, S. (2017) · arXiv · doi:10.48550/arxiv.1703.03400 · Cited by 8,512
FCOS: Fully Convolutional One-Stage Object Detection
Tian, Z., Shen, C., Chen, H., & He, T. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00972 · Cited by 7,013 · cited 1×
“FCOS-based Methods: Similarly, recent works have adopted itasabackboneduetothestrongperformanceandclass-agnostic localizationcapabilityofFCOS[104].”
(2017) · International Conference on Machine Learning · Cited by 6,382
Selective Search for Object Recognition
Uijlings, J. R. R., van de Sande, K. E. A., Gevers, T., & Smeulders, A. W. M. (2013) · International Journal of Computer Vision · doi:10.1007/s11263-013-0620-5 · Cited by 5,980 · cited 1×
“…was pre-trained using a large amount of data from the base classes, and the class-specific components of DETR (including the projection layer andclassificationheadforspecificclasses)werefine-tunedusing self-supervisionfromadditionalobjectproposalsgeneratedby selectivesearchalgorithm[108]aspseudolabels.”
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1512.03385 · Cited by 4,196
iCaRL: Incremental Classifier and Representation Learning
Rebuffi, S.-A., Kolesnikov, A., Sperl, G., & Lampert, C. H. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.587 · Cited by 3,988 · cited 1×
“The first uses a feature extractor with a softmax classifier, while the second involves a feature embedding network and the nearest class mean classifier [22], [42], [43].”
Knowledge Distillation: A Survey
Gou, J., Yu, B., Maybank, S. J., & Tao, D. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-021-01453-z · Cited by 3,931 · cited 1×
“2) Knowledge Distillation-Based Methods: In continuous learning, KD is widely employed to transfer knowledge from an old model, known as the “teacher model,” to a new model, referred to as the “student model” [91].”
Kuznetsova, A., Rom, H., Alldrin, N., Uijlings, J., Krasin, I., Pont-Tuset, J., Kamali, S., Popov, S., Malloci, M., Kolesnikov, A., et al. (2018) · arXiv · doi:10.48550/arxiv.1811.00982 · Cited by 3,653
He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2844175 · Cited by 3,457
Generalizing from a Few Examples: A Survey on Few-shot Learning
Wang, Y., Yao, Q., Kwok, J. T., & Ni, L. M. (2021) · ACM Computing Surveys · doi:10.1145/3386252 · Cited by 3,165
Optimization Methods for Large-Scale Machine Learning
Bottou, L., Curtis, F. E., & Nocedal, J. (2018) · SIAM Review · doi:10.1137/16m1080173 · Cited by 3,128 · cited 1×
“Toelaborateonthischallenge,weintroduceessentialcon-cepts of empirical risk minimization [27], [40], [41].”
Continual lifelong learning with neural networks: A review
Parisi, G. I., Kemker, R., Part, J. L., Kanan, C., & Wermter, S. (2019) · Neural Networks · doi:10.1016/j.neunet.2019.01.012 · Cited by 3,117
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Bourdev, L., Girshick, R., Hays, J., Perona, P., Ramanan, D., Zitnick, C. L., & Dollár, P. (2014) · arXiv · doi:10.48550/arxiv.1405.0312 · Cited by 2,579
Zhang, S., Chi, C., Yao, Y., Lei, Z., & Li, S. Z. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00978 · Cited by 2,354 · cited 1×
“Inthiswork,FCOSandATSS[106]wereemployedas thebaselinedetectors.”
Kuznetsova, A., Rom, H., Alldrin, N., Uijlings, J., Krasin, I., Pont-Tuset, J., Kamali, S., Popov, S., Malloci, M., Kolesnikov, A., et al. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-020-01316-z · Cited by 1,738
A Continual Learning Survey: Defying Forgetting in Classification Tasks
Delange, M., Aljundi, R., Masana, M., Parisot, S., Jia, X., Leonardis, A., Slabaugh, G., & Tuytelaars, T. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3057446 · Cited by 1,647 · cited 7×
“AlthoughsomesurveysbrieflymentionFSCIL[32], [35],theyonlyprovideashortintroductiontotheconceptanda fewstudieswithoutofferingathoroughorsystematicanalysis.”
InfluentialA continual learning survey: Defying forgetting in classification tasks
De Lange, M., Aljundi, R., Masana, M., Parisot, S., Jia, X., Leonardis, A., Slabaugh, G., & Tuytelaars, T. (2019) · arXiv · doi:10.48550/arxiv.1909.08383 · Cited by 1,647
Large Scale Incremental Learning
Wu, Y., Chen, Y., Wang, L., Ye, Y., Liu, Z., Guo, Y., & Fu, Y. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00046 · Cited by 1,313
PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning
Mallya, A., & Lazebnik, S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00810 · Cited by 1,258 · cited 1×
“To avert catastrophic forgetting, various algorithms [11], [48], [49] employ task-specific components or design separate networks for each task.”
The Tradeoffs of Large-Scale Learning
Bottou, L., & Bousquet, O. (2011) · Optimization for Machine Learning · doi:10.7551/mitpress/8996.003.0015 · Cited by 1,128
Dynamic Few-Shot Visual Learning Without Forgetting
Gidaris, S., & Komodakis, N. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00459 · Cited by 1,128
A Comprehensive Survey of Continual Learning: Theory, Method and Application
Wang, L., Zhang, X., Su, H., & Zhu, J. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3367329 · Cited by 1,113
An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
Goodfellow, I. J., Mirza, M., Xiao, D., Courville, A., & Bengio, Y. (2013) · arXiv · doi:10.48550/arxiv.1312.6211 · Cited by 1,089
Meta-Learning in Neural Networks: A Survey
Hospedales, T. M., Antoniou, A., Micaelli, P., & Storkey, A. J. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3079209 · Cited by 886 · cited 1×
“Meta-learning leverages experiences distilled from multiple learning episodes, encompassing a distribution of related tasks, to enhance future learning performance [94].”
Meta-Learning in Neural Networks: A Survey
Hospedales, T., Antoniou, A., Micaelli, P., & Storkey, A. (2020) · arXiv · doi:10.48550/arxiv.2004.05439 · Cited by 886 · cited 1×
“Meta-learning leverages experiences distilled from multiple learning episodes, encompassing a distribution of related tasks, to enhance future learning performance [94].”
Matching Networks for One Shot Learning
Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., & Wierstra, D. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.04080 · Cited by 854
Class-Incremental Learning: Survey and Performance Evaluation on Image Classification
Masana, M., Liu, X., Twardowski, B., Menta, M., Bagdanov, A. D., & van de Weijer, J. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3213473 · Cited by 740 · cited 4×
“IL, also termed continual or lifelong learning, enables systems to learn new tasks over time while maintaining previous knowledge [5], [6], [7], aiming to replicate human learning abilities [5].”
InfluentialA Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities
Song, Y., Wang, T., Cai, P., Mondal, S. K., & Sahoo, J. P. (2023) · ACM Computing Surveys · doi:10.1145/3582688 · Cited by 721
Deep Metric Learning: A Survey
KAYA, M., & BİLGE, H. Ş. (2019) · Symmetry · doi:10.3390/sym11091066 · Cited by 703 · cited 1×
“Metric Learning-based Methods: Metric learning aims to determine the similarity between objects using an optimal distance metric for learning tasks [77].”
Three types of incremental learning
van de Ven, G. M., Tuytelaars, T., & Tolias, A. S. (2022) · Nature Machine Intelligence · doi:10.1038/s42256-022-00568-3 · Cited by 665 · cited 7×
“To avert catastrophic forgetting, various algorithms [11], [48], [49] employ task-specific components or design separate networks for each task.”
InfluentialAn Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild
Chao, W.-L., Changpinyo, S., Gong, B., & Sha, F. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46475-6_4 · Cited by 616 · cited 1×
“However, real-world applications often require models to learn new classes from limited samples while maintaining performance on base classes, which often represent high-frequency classes in the real world [13], [54].”
Low-Shot Learning with Imprinted Weights
Qi, H., Brown, M., & Lowe, D. G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00610 · Cited by 539 · cited 1×
“This practical need has led to the development of a novel setting, gFSL [15], aimed at enabling learning of new classes with limited samples without compromising performance on previous classes [15], [55], [56].”
Sequential updating of conditional probabilities on directed graphical structures
Spiegelhalter, D. J., & Lauritzen, S. L. (1990) · Networks · doi:10.1002/net.3230200507 · Cited by 521 · cited 1×
“Furthermore, Nguyen and Todorovic [109] extended the Mask R-CNN framework in the second stage: a new object class classifier based on the probit function [113] and a new uncertainty-guided bounding box predictor.”
Lesort, T., Lomonaco, V., Stoian, A., Maltoni, D., Filliat, D., & Díaz-Rodríguez, N. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.12.004 · Cited by 506
Few-Shot Class-Incremental Learning
Tao, X., Hong, X., Chang, X., Dong, S., Wei, X., & Gong, Y. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01220 · Cited by 499 · cited 9×
“FSCIL was first carried out by TOPIC [13].”
InfluentialOnline continual learning in image classification: An empirical survey
Mai, Z., Li, R., Jeong, J., Quispe, D., Kim, H., & Sanner, S. (2022) · Neurocomputing · doi:10.1016/j.neucom.2021.10.021 · Cited by 410 · cited 1×
“DespiteexistingsurveysonFSL[27],[28],[29],[30]and IL[5],[6],[7],[11],[31],[32],[33],[34],[35],thereisa clearlackofsystematicandcomprehensivesurveysspecifically onFSCIL.”
Prevalence of neural collapse during the terminal phase of deep learning training
Papyan, V., Han, X. Y., & Donoho, D. L. (2020) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2015509117 · Cited by 403 · cited 1×
“9(b), Yang et al. [82] proposed an FSCIL framework based on neural collapse [83], which refers to the phenomenon that at the end of training (after 0 training error rate), the last layer features of the same class collapse into a single vertex in the feature space, aligning all class vertices with…”
Few-Shot Incremental Learning with Continually Evolved Classifiers
Zhang, C., Song, N., Lin, G., Zheng, Y., Pan, P., & Xu, Y. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01227 · Cited by 382
Class-Incremental Learning: A Survey
Zhou, D.-W., Wang, Q.-W., Qi, Z.-H., Ye, H.-J., Zhan, D.-C., & Liu, Z. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3429383 · Cited by 376 · cited 3×
“[34]summarizedtheCILproblem fromperspectiveslikeDR,DataRegularization,andDynamic Networks.”
Semantic Drift Compensation for Class-Incremental Learning
Yu, L., Twardowski, B., Liu, X., Herranz, L., Wang, K., Cheng, Y., Jui, S., & van de Weijer, J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00701 · Cited by 340 · cited 1×
“The first uses a feature extractor with a softmax classifier, while the second involves a feature embedding network and the nearest class mean classifier [22], [42], [43].”
Continuous learning in single-incremental-task scenarios
Maltoni, D., & Lomonaco, V. (2019) · Neural Networks · doi:10.1016/j.neunet.2019.03.010 · Cited by 309 · cited 1×
“To avert catastrophic forgetting, various algorithms [11], [48], [49] employ task-specific components or design separate networks for each task.”
Frustratingly Simple Few-Shot Object Detection
Wang, X., Huang, T. E., Darrell, T. J., Gonzalez, J. E., & Yu, F. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.06957 · Cited by 296
Zhou, X., Wang, D., & Krähenbühl, P. (2019) · arXiv · doi:10.48550/arxiv.1904.07850 · Cited by 288 · cited 1×
“CentreNet-based Methods: CentreNet [103] redefined object detection as a point + attribute regression problem.”
Forward Compatible Few-Shot Class-Incremental Learning
Zhou, D.-W., Wang, F.-Y., Ye, H.-J., Ma, L., Pu, S., & Zhan, D.-C. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00884 · Cited by 281
Competitive Hebbian Learning Rule Forms Perfectly Topology Preserving Maps
Martinetz, T. (1993) · ICANN ’93 · doi:10.1007/978-1-4471-2063-6_104 · Cited by 256 · cited 1×
“Specifically, the neural gas network defined an undirected graph that mapped the feature space to a finite set of feature vectors and maintained the topological properties of the feature space through competitive Hebbian learning [70].”
Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning
Yang, Y., Yuan, H., Li, X., Lin, Z., Torr, P. H. S., & Tao, D. (2023) · Oxford University Research Archive (ORA) (University of Oxford) · doi:10.48550/arxiv.2302.03004 · Cited by 248
Deep metric learning for few-shot image classification: A Review of recent developments
Li, X., Yang, X., Ma, Z., & Xue, J.-H. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.109381 · Cited by 243
Biological underpinnings for lifelong learning machines
Kudithipudi, D., Aguilar-Simon, M., Babb, J., Bazhenov, M., Blackiston, D., Bongard, J., Brna, A. P., Chakravarthi Raja, S., Cheney, N., Clune, J., et al. (2022) · Nature Machine Intelligence · doi:10.1038/s42256-022-00452-0 · Cited by 236 · cited 1×
“Currently, some IL research, such as the method proposed by ZKudithipudi et al. [115] that emulates the Drosophila’s mush-room body’s mechanisms, attempts to enhance model memory capabilities by bio-inspired intelligence.”
A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks
Belouadah, E., Popescu, A., & Kanellos, I. (2020) · arXiv · doi:10.48550/arxiv.2011.01844 · Cited by 235 · cited 2×
“AlthoughsomesurveysbrieflymentionFSCIL[32], [35],theyonlyprovideashortintroductiontotheconceptanda fewstudieswithoutofferingathoroughorsystematicanalysis.”
A survey on few-shot class-incremental learning
Tian, S., Li, L., Li, W., Ran, H., Ning, X., & Tiwari, P. (2024) · Neural Networks · doi:10.1016/j.neunet.2023.10.039 · Cited by 220
Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat MinimaPreprint
Shi, G., Chen, J., Zhang, W., Zhan, L.-M., & Wu, X.-M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.01549 · Cited by 206
Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning
Cheraghian, A., Rahman, S., Fang, P., Roy, S. K., Petersson, L., & Harandi, M. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00256 · Cited by 201 · cited 4×
“The role of attention modules used in many FSCIL approaches [14], [16], [17], [73], [74] is diverse.”
InfluentialIncremental Few-Shot Learning with Attention Attractor NetworksPreprint
Ren, M., Liao, R., Fetaya, E., & Zemel, R. S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.07218 · Cited by 181
Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning
Zhu, K., Cao, Y., Zhai, W., Cheng, J., & Zha, Z.-J. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00673 · Cited by 179 · cited 2×
“In Table IV, the top five methods with the lowest PD values on mini ImageNet are: MgSvF [22] (17.33%), SFbFSCIL [79] (19.14%), SPPR [69] (19.53%), ERL++ [92] (20.94%), and DSN (21.06%).”
InfluentialA Closer Look at Few-shot Classification
Chen, W.-Y., Liu, Y., Kira, Z., Wang, Y.-C. F., & Huang, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.04232 · Cited by 174
Towards Robust Evaluations of Continual Learning
Farquhar, S., & Gal, Y. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.09733 · Cited by 169
Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration
Wang, Q., Zhou, D.-W., Zhang, Y.-K., Zhan, D.-C., & Ye, H.-J. (2023) · neural information processing systems · doi:10.52202/075280-0661 · Cited by 169
Constrained Few-shot Class-incremental Learning
Hersche, M., Karunaratne, G., Cherubini, G., Benini, L., Sebastian, A., & Rahimi, A. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00885 · Cited by 167 · cited 3×
“For instance, in the C-FSCIL framework proposed by Hersche et al. [24], empirical evidence demonstrated that training the backbone using the meta-learning strategy effectively can extract robust features.”
InfluentialFew-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay
Liu, H., Gu, L., Chi, Z., Wang, Y., Yu, Y., Chen, J., & Tang, J. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20053-3_9 · Cited by 167
MetaFSCIL: A Meta-Learning Approach for Few-Shot Class Incremental Learning
Chi, Z., Gu, L., Liu, H., Wang, Y., Yu, Y., & Tang, J. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01377 · Cited by 164
Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks
Zhou, D.-W., Ye, H.-J., Ma, L., Xie, D., Pu, S., & Zhan, D.-C. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3200865 · Cited by 162 · cited 6×
“This process is formulated as follows: wherethecurrentFSCILalgorithm f aimstobuiltthenewmodel based on the dataset D btrain and previous model parameters θ b − 1 and minimize the loss L on all seen classes [16].”
InfluentialFew-Shot Class-Incremental Learning via Relation Knowledge Distillation
Dong, S., Hong, X., Tao, X., Chang, X., Wei, X., & Gong, Y. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i2.16213 · Cited by 161 · cited 3×
“In Table IV, the top five methods with the lowest PD values on mini ImageNet are: MgSvF [22] (17.33%), SFbFSCIL [79] (19.14%), SPPR [69] (19.53%), ERL++ [92] (20.94%), and DSN (21.06%).”
InfluentialThe Devil Is in the Details: Self-supervised Attention for Vehicle Re-identification
Khorramshahi, P., Peri, N., Chen, J.-C., & Chellappa, R. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58568-6_22 · Cited by 158 · cited 1×
“For example, inspired by the frequency decoupling [81], Zhao et al. [22] discussed and utilized the characteristics of different frequency components in features.”
Few-Shot Object Detection: A Survey
Antonelli, S., Avola, D., Cinque, L., Crisostomi, D., Foresti, G. L., Galasso, F., Marini, M. R., Mecca, A., & Pannone, D. (2022) · ACM Computing Surveys · doi:10.1145/3519022 · Cited by 121
Mazumder, P., Singh, P., & Rai, P. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i3.16334 · Cited by 119 · cited 3×
“FSLL+SS [21] introduced the semi-supervised features to FSCIL for the first time.”
Dynamic Support Network for Few-Shot Class Incremental Learning
Yang, B., Lin, M., Zhang, Y., Liu, B., Liang, X., Ji, R., & Ye, Q. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3175849 · Cited by 119 · cited 5×
“For example, Yang et al. proposed a series of works [25], [71].”
InfluentialSong, Z., Zhao, Y., Shi, Y., Peng, P., Yuan, L., & Tian, Y. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.02316 · Cited by 116 · cited 1×
“From the analysis of SA across the three datasets in Table IV, it can be seen that the top five methods on mini ImageNet are: SAVC [96] (81.12%), ALICE [47] (80.60%), BiDistFSCIL [73] (74.65%), TEEN [97] (73.53%), and CLOM [26] (73.08%).”
InfluentialMgSvF: Multi-Grained Slow versus Fast Framework for Few-Shot Class-Incremental Learning
Zhao, H., Fu, Y., Kang, M., Tian, Q., Wu, F., & Li, X. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3133897 · Cited by 115
Klein, S. B. (2015) · WIREs Cognitive Science · doi:10.1002/wcs.1333 · Cited by 112
Meta-Learning-Based Incremental Few-Shot Object Detection
Cheng, M., Wang, H., & Long, Y. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3088545 · Cited by 111 · cited 2×
“1) Anchor-Free Frameworks: Recently, some studies [62], [99],[100],[101],[102]haveadoptedanchor-freeframeworksto performthistask.”
Few-Shot Class-Incremental Learning from an Open-Set Perspective
Peng, C., Zhao, K., Wang, T., Li, M., & Lovell, B. C. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-19806-9_22 · Cited by 110
Few-Shot Class-Incremental Learning via Class-Aware Bilateral Distillation
Zhao, L., Lu, J., Xu, Y., Cheng, Z., Guo, D., Niu, Y., & Fang, X. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01139 · Cited by 109 · cited 5×
“The role of attention modules used in many FSCIL approaches [14], [16], [17], [73], [74] is diverse.”
InfluentialMargin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation
Zou, Y., Zhang, S., Li, Y., & Li, R. (2022) · neural information processing systems · doi:10.52202/068431-1977 · Cited by 105
A Survey of Self-Supervised and Few-Shot Object Detection
Huang, G., Laradji, I., Vazquez, D., Lacoste-Julien, S., & Rodriguez, P. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3199617 · Cited by 100
A survey on machine learning from few samples
Lu, J., Gong, P., Ye, J., Zhang, J., & Zhang, C. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.109480 · Cited by 100
Self-citationDynamic Few-Shot Visual Learning without ForgettingPreprint
Gidaris, S., & Komodakis, N. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.09458 · Cited by 76
Incremental Few-Shot Instance Segmentation
Ganea, D. A., Boom, B., & Poppe, R. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00124 · Cited by 74 · cited 4×
“…to the classification task in FSCIL, FSCIOD aims to enable the model to continuously learn new classes from limited samples while achieving accurate localization (using bounding box regression or segmentation) and classification of each corresponding individual object in an image [98], [99], [100].”
InfluentialKukleva, A., Kuehne, H., & Schiele, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00889 · Cited by 73 · cited 3×
“LCwoF [18] and ERDFR [19] proposed distinct Data Replay (DR) strategies.”
Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learning
Dong, N., Zhang, Y., Ding, M., & Lee, G. (2022) · AAAI Conference on Artificial Intelligence · doi:10.48550/arxiv.2205.04042 · Cited by 67
Memorizing Complementation Network for Few-Shot Class-Incremental Learning
Ji, Z., Hou, Z., Liu, X., Pang, Y., & Li, X. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3236160 · Cited by 65 · cited 1×
“The FSCIL aims to learn an ML model that can continuously learn knowledge from a sequence of new classes with only a few labeled training samples while preserving the knowledge gained from previous classes [13], [14], [37], [38].”
Synthesized Feature based Few-Shot Class-Incremental Learning on a Mixture of Subspaces
Cheraghian, A., Rahman, S., Ramasinghe, S., Fang, P., Simon, C., Petersson, L., & Harandi, M. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00854 · Cited by 64 · cited 2×
“In Table IV, the top five methods with the lowest PD values on mini ImageNet are: MgSvF [22] (17.33%), SFbFSCIL [79] (19.14%), SPPR [69] (19.53%), ERL++ [92] (20.94%), and DSN (21.06%).”
InfluentialWang, L., Yang, X., Tan, H., Bai, X., & Zhou, F. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3248040 · Cited by 64
Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learning
Dong, N., Zhang, Y., Ding, M., & Lee, G. H. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i1.25129 · Cited by 62
Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detection
Yin, L., Perez-Rua, J. M., & Liang, K. J. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00883 · Cited by 56 · cited 5×
“1) Anchor-Free Frameworks: Recently, some studies [62], [99],[100],[101],[102]haveadoptedanchor-freeframeworksto performthistask.”
InfluentialIncremental Few-Shot Object Detection
Perez-Rua, J.-M., Zhu, X., Hospedales, T. M., & Xiang, T. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01386 · Cited by 55
Semantics-Driven Generative Replay for Few-Shot Class Incremental Learning
Agarwal, A., Banerjee, B., Cuzzolin, F., & Chaudhuri, S. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3548160 · Cited by 52
XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot LearningPreprint
Yoon, S. W., Kim, D.-Y., Seo, J. S., & Moon, J. J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.08561 · Cited by 51
Self-supervised Label Augmentation via Input Transformations
Lee, H., Hwang, S. J., & Shin, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.05872 · Cited by 51
CRNet: A Fast Continual Learning Framework With Random Theory
Li, D., & Zeng, Z. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3262853 · Cited by 46 · cited 1×
“This field has seen growing interest recently, prompting numerous studies and surveys [5], [7], [8], [9], [10], [11].”
S3C: Self-Supervised Stochastic Classifiers for Few-Shot Class-Incremental Learning
Kalla, J., & Biswas, S. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-19806-9_25 · Cited by 45 · cited 4×
“Notably, a significant focus is on incorporating self-supervised features into the fusion process [21], [72], [85], [86].”
InfluentialUncertainty-Guided Semi-Supervised Few-Shot Class-Incremental Learning With Knowledge Distillation
Cui, Y., Deng, W., Xu, X., Liu, Z., Liu, Z., Pietikäinen, M., & Liu, L. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3208743 · Cited by 44 · cited 3×
“To mitigate catastrophic forgetting, some studies [44], [45], [46] use KD to maintain competent classification capabilities on previous classes while learning new ones.”
Self-citationiFS-RCNN: An Incremental Few-shot Instance Segmenter
Nguyen, K., & Todorović, S. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00688 · Cited by 44 · cited 3×
“2) Anchor-Based Frameworks: In addition to anchor-free frameworks, there have been some studies [98], [109] that adopt the anchor-based framework, Mask R-CNN [110], to address object detection and instance segmentation in FSCIL.”
Heterogeneous Few-Shot Model Rectification With Semantic Mapping
Ye, H.-J., Zhan, D., Jiang, Y. Y., & Zhou, Z. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2994749 · Cited by 43
CBA: Improving Online Continual Learning via Continual Bias Adaptor
Wang, Q., Wang, R., Wu, Y., Jia, X., & Meng, D. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01749 · Cited by 42
Few-Shot Class Incremental Learning Leveraging Self-Supervised Features
Ahmad, T., Dhamija, A. R., Cruz, S., Rabinowitz, R., Li, C., Jafarzadeh, M., & Boult, T. E. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00435 · Cited by 41 · cited 4×
“Furthermore, in the framework proposed by Ahmad et al. [72], the output nodes of the model increased with the number of classes involved in the current session.”
InfluentialMultimodal Parameter-Efficient Few-Shot Class Incremental Learning
D’Alessandro, M., Alonso, A., Calabrés, E., & Galar, M. (2023) · 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw60793.2023.00364 · Cited by 40
Uncertainty-Aware Distillation for Semi-Supervised Few-Shot Class-Incremental Learning
Cui, Y., Deng, W., Chen, H., & Liu, L. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3277018 · Cited by 39 · cited 3×
“To mitigate catastrophic forgetting, some studies [44], [45], [46] use KD to maintain competent classification capabilities on previous classes while learning new ones.”
Self-citationWhat Can Knowledge Bring to Machine Learning?—A Survey of Low-shot Learning for Structured Data
Hu, Y., Chapman, A. P., Wen, G., & Hall, D. W. (2022) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3510030 · Cited by 36
Pan, Z., Yu, X., Zhang, M., & Gao, Y. (2023) · 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv56688.2023.00621 · Cited by 28 · cited 1×
“Some studies, such as [64], have introduced datasets for various FSCIL scenarios, but there remains significant scope for dataset enhancement.”
Learnable Expansion-and-Compression Network for Few-shot Class-Incremental LearningPreprint
Yang, B., Lin, M., Liu, B., Fu, M., Liu, C., Ji, R., & Ye, Q. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.02281 · Cited by 25
Few-Shot Class-Incremental Learning for Retinal Disease Recognition
Zhang, J., Zhao, P., Zhao, Y., Li, C., & Hu, D. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3457915 · Cited by 23
Self-citationIncremental few-shot object detection via knowledge transfer
Feng, H., Zhang, L., Yang, X., & Liu, Z. (2022) · Pattern Recognition Letters · doi:10.1016/j.patrec.2022.01.024 · Cited by 22 · cited 4×
“It can be found from Table V, the top three performance methods for object detection achieved on base classes are Sylph [99], iFS-RCNN [109], and MCH [102].”
InfluentialFew-Shot Class-Incremental Learning with Meta-Learned Class Structures
Zheng, G., & Zhang, A. (2021) · 2021 International Conference on Data Mining Workshops (ICDMW) · doi:10.1109/icdmw53433.2021.00058 · Cited by 19
Variable Few Shot Class Incremental and Open World Learning
Ahmad, T., Dhamija, A. R., Jafarzadeh, M., Cruz, S., Rabinowitz, R., Li, C., & Boult, T. E. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00413 · Cited by 19 · cited 1×
“Notably, a significant focus is on incorporating self-supervised features into the fusion process [21], [72], [85], [86].”
Semi-Supervised Few-Shot Class-Incremental Learning
Cui, Y., Xiong, W., Tavakolian, M., & Liu, L. (2021) · 2021 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip42928.2021.9506346 · Cited by 16 · cited 2×
“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-citationFew-Shot Class Incremental Learning with Generative Feature Replay
Shankarampeta, A., & Yamauchi, K. (2021) · International Conference on Pattern Recognition Applications and Methods · doi:10.5220/0010246602590267 · Cited by 7 · cited 1×
“Specifi-cally, Shankarampeta and Yamauchi [65] proposed a framework basedonWassersteinGAN[66]withMAML[67],whichmainly consistedofafeatureextractorandafeaturegenerator.”
Few-shot class-incremental learning based on representation enhancement
Yao, G., Zhu, J., Zhou, W., & Li, J. (2022) · Journal of Electronic Imaging · doi:10.1117/1.jei.31.4.043027 · Cited by 6 · cited 1×
“[90]proposed asimplestrategyforenhancingthenewprototype.”
Feature Distribution Distillation-Based Few Shot Class Incremental Learning
Zhu, J., Yao, G., Zhou, W., Zhang, G., Ping, W., & Zhang, W. (2022) · 2022 5th International Conference on Pattern Recognition and Artificial Intelligence (PRAI) · doi:10.1109/prai55851.2022.9904282 · Cited by 6
Research works printed but not linked: 2
- Kim, Warping the space: Weight space rotation for class-incremental few-shot learning
- Neal, 2012, Bayesian Learning for Neural Networks, 118
Cited by
Raza, A., Hanif, F., & Mohammed, H. A. (2025) · Scientific Reports · doi:10.1038/s41598-025-26645-2 · Cited by 56
“Transformer-based detectors (Deformable DETR, RT-DETR, PVT backbones) demonstrably improve small-object recall and occlusion robustness and can reach competitive speed–accuracy trade-offs when engineered for throughput (RT-DETR reports AP ∼ 53.1% on COCO and high FPS on T4). tasks They are particularly valuable for de…”
InfluentialYang, Y., Qu, J., Dong, W., Huang, L., & Li, Y. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3650395 · Cited by 22
“Existing FSCIL methods can be classified into five categories: 1) feature-based methods; 2) meta-learning methods; 3) replay-based methods; 4) dynamic and prompt-based methods; and 5) regularization-based methods [30].”
Liu, Y., Jiang, T., Li, R., Yuan, L., Grzegorzek, M., Li, C., & Li, X. (2025) · Frontiers in Medicine · doi:10.3389/fmed.2025.1551894 · Cited by 16
Scale-Dependent Performance Analysis of YOLO26 and YOLOv11 for PPE Detection
Yavuz, B. Ç. (2026) · Electronics · doi:10.3390/electronics15061146 · Cited by 15
WP-FSCIL: A Well-Prepared Few-Shot Class-Incremental Learning Framework for Pill Recognition
Zhang, J., Li, C., Cristani, M., Sun, H., Grzegorzek, M., & Chen, H. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3548691 · Cited by 10
“…which measures the absolute decline in accuracy from the first session to the last, calculated as PD = A 0 − A N , where A 0 represents the classification accuracy in the base session, and A N represents the accuracy in the final session [41]; and 3) The Average Accuracy (AA) across all sessions.”
Self-citation
Metadata
- Authors
- Zhang, J., Liu, L., Silvén, O., Pietikäinen, M., & Hu, D.
- Affiliations
- National University of Defense Technology (CN)
- CMVS, University of Oulu, Oulu, Finland
- University of Oulu (FI)
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2025-04
- Volume
- 47
- Issue
- 4
- Pages
- 2924-2945
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W4406354592
- Semantic Scholar
- 7dbb2b74102b7bf25c2a616e68340129d6775d3a
- Cited by
- 84
- References
- 123
- Citations by year
- 2026: 58 · 2025: 24
- FWCI
- 32.63
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (62036013, 62376283)
- Science and Technology Innovation Program of Hunan Province (2024QK2006)
- Key Stone (JS2023-03)
- National University of Defense Technology
- 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 Data Classification
- Keywords
- few-shot class-incremental learning, class-incremental learning, few-shot learning, object detection, classification, catastrophic forgetting, stability-plasticity dilemma, benchmark dataset, evaluation metrics, anchor-free detection, anchor-based detection
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-29, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-29 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.