{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T05:54:47Z","timestamp":1784872487773,"version":"3.55.0"},"reference-count":42,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T00:00:00Z","timestamp":1779148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Few-Shot Class-Incremental Learning (FSCIL) aims to learn new classes with only a few samples, making it more challenging than traditional Class-Incremental Learning (CIL) due to the scarcity of available samples. The imbalance in sample distribution further complicates balancing the abundant base data with the scarce incremental data. While the model must fully leverage the extensive base data to guide the learning of subsequent tasks, it must also avoid over-relying on these data, as doing so could degrade its generalization capability and impede the learning of new incremental tasks. To address these challenges, we propose a novel framework for few-shot incremental learning, incorporating tailored prompt alignment strategies for both the base and incremental session. In the base session, we strike a balance between task-specific and task-agnostic knowledge to preserve the model\u2019s generalization ability. In the incremental session, we mitigate the overfitting issue typically associated with few-shot learning. Furthermore, to tackle the prototype network bias caused by the imbalance in sample distribution, we propose a subspace prototype aggregation module, which effectively alleviates prediction bias in the incremental phase. Extensive experiments conducted on three benchmark datasets\u2014CIFAR-100, miniImageNet, and CUB-200\u2014demonstrate that our approach achieves state-of-the-art (SOTA) performance in FSCIL.<\/jats:p>","DOI":"10.3390\/a19050407","type":"journal-article","created":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T11:53:10Z","timestamp":1779191590000},"page":"407","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Few-Shot Class-Incremental Learning with Prompt Alignment and Subspace Prototype Aggregation"],"prefix":"10.3390","volume":"19","author":[{"given":"Qiang","family":"Huang","sequence":"first","affiliation":[{"name":"School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang 212013, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,19]]},"reference":[{"key":"ref_1","unstructured":"Masana, M., Liu, X., Twardowski, B., Menta, M., Bagdanov, A.D., and van de Weijer, J. (2020). Class-incremental learning: Survey and performance evaluation on image classification. arXiv."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Delange, M., Aljundi, R., Masana, M., Parisot, S., Jia, X., Leonardis, A., Slabaugh, G., and Tuytelaars, T. (2021). A continual learning survey: Defying forgetting in classification tasks. TPAMI, in press.","DOI":"10.1109\/TPAMI.2021.3057446"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2935","DOI":"10.1109\/TPAMI.2017.2773081","article-title":"Learning without forgetting","volume":"40","author":"Li","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Rebuffi, S.A., Kolesnikov, A., Sperl, G., and Lampert, C.H. (2017). icarl: Incremental classifier and representation learning. Proceedings of the CVPR, IEEE.","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"Kirkpatrick","year":"2017","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Aljundi, R., Babiloni, F., Elhoseiny, M., Rohrbach, M., and Tuytelaars, T. (2018). Memory aware synapses: Learning what (not) to forget. Computer Vision\u2014ECCV 2018: 15th European Conference, Munich, Germany, 8\u201314 September 2018, Proceedings, Part III, Springer.","DOI":"10.1007\/978-3-030-01219-9_9"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Mermillod, M., Bugaiska, A., and Bonin, P. (2013). The stability-plasticity dilemma: Investigating the continuum from catastrophic forgetting to age-limited learning effects. Front. Psychol., 4.","DOI":"10.3389\/fpsyg.2013.00504"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/j.neunet.2023.10.039","article-title":"A survey on few-shot class-incremental learning","volume":"169","author":"Tian","year":"2024","journal-title":"Neural Netw."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Chi, Z., Gu, L., Liu, H., Wang, Y., Yu, Y., and Tang, J. (2022). MetaFSCIL: A Meta-Learning Approach for Few-Shot Class Incremental Learning. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52688.2022.01377"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Cheraghian, A., Rahman, S., Fang, P., Roy, S.K., Petersson, L., and Harandi, M. (2021). Semantic-Aware Knowledge Distillation for Few-Shot Class-Incremental Learning. Proceedings of the CVPR, IEEE.","DOI":"10.1109\/CVPR46437.2021.00256"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"12816","DOI":"10.1109\/TPAMI.2022.3200865","article-title":"Few-shot class-incremental learning by sampling multi-phase tasks","volume":"45","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhang, Z., Ebrahimi, S., Sun, R., Zhang, H., Lee, C.Y., Ren, X., Su, G., Perot, V., and Dy, J. (2022). Dualprompt: Complementary prompting for rehearsal-free continual learning. Proceedings of the European Conference on Computer Vision (ECCV), Springer.","DOI":"10.1007\/978-3-031-19809-0_36"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhang, Z., Lee, C.Y., Zhang, H., Sun, R., Ren, X., Su, G., Perot, V., Dy, J., and Pfister, T. (2022). Learning to Prompt for Continual Learning. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Smith, J.S., Karlinsky, L., Gutta, V., Cascante-Bonilla, P., Kim, D., Arbelle, A., Panda, R., Feris, R., and Kira, Z. (2023). CODA-Prompt: COntinual Decomposed Attention-Based Prompting for Rehearsal-Free Continual Learning. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52729.2023.01146"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Liu, C., Wang, Z., Xiong, T., Chen, R., Wu, Y., Guo, J., and Huang, H. (2024). Few-Shot Class Incremental Learning with Attention-Aware Self-Adaptive Prompt. arXiv.","DOI":"10.1007\/978-3-031-73004-7_1"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"D\u2019Alessandro, M., Alonso, A., Calabr\u00e9s, E., and Galar, M. (2023). Multimodal parameter-efficient few-shot class incremental learning. IEEE\/CVF International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCVW60793.2023.00364"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Wasim, S.T., Naseer, M., Khan, S., Yang, M.H., and Khan, F.S. (2023). Self-regulating prompts: Foundational model adaptation without forgetting. IEEE\/CVF International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"ref_18","unstructured":"van de Ven, G.M., and Tolias, A.S. (2019). Three scenarios for continual learning. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Wu, Y., Chen, Y., Wang, L., Ye, Y., Liu, Z., Guo, Y., and Fu, Y. (2019). Large scale incremental learning. Proceedings of the CVPR, IEEE.","DOI":"10.1109\/CVPR.2019.00046"},{"key":"ref_20","unstructured":"Chaudhry, A., Ranzato, M., Rohrbach, M., and Elhoseiny, M. (2019). Efficient Lifelong Learning with A-GEM. Proceedings of the ICLR, Curran Associates, Inc."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Fu, Y., Ji, P., and Huang, H. (2019). Incremental learning using conditional adversarial networks. Proceedings of the ICCV, IEEE.","DOI":"10.1109\/ICCV.2019.00672"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Iscen, A., Zhang, J., Lazebnik, S., and Schmid, C. (2020). Memory-efficient incremental learning through feature adaptation. Proceedings of the ECCV, Springer.","DOI":"10.1007\/978-3-030-58517-4_41"},{"key":"ref_23","unstructured":"Hinton, G., Vinyals, O., and Dean, J. (2015). Distilling the knowledge in a neural network. Proceedings of the NeurIPS Workshop, Neural Information Processing Systems Foundation, Inc."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Zhao, L., Lu, J., Xu, Y., Cheng, Z., Guo, D., Niu, Y., and Fang, X. (2023). Few-shot class-incremental learning via class-aware bilateral distillation. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52729.2023.01139"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Tao, X., Hong, X., Chang, X., Dong, S., Wei, X., and Gong, Y. (2020). Few-shot class-incremental learning. Proceedings of the CVPR, IEEE.","DOI":"10.1109\/CVPR42600.2020.01220"},{"key":"ref_26","unstructured":"Shi, G., Chen, J., Zhang, W., Zhan, L.M., and Wu, X.M. (2021). Overcoming catastrophic forgetting in incremental few-shot learning by finding flat minima. Advances in Neural Information Processing Systems (NeurIPS), Neural Information Processing Systems Foundation, Inc."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Zhou, D.W., Wang, F.Y., Ye, H.J., Ma, L., Pu, S., and Zhan, D.C. (2022). Forward compatible few-shot class-incremental learning. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52688.2022.00884"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Mazumder, P., Singh, P., and Rai, P. (2021). Few-Shot Lifelong Learning. Proceedings of the AAAI, AAAI Press.","DOI":"10.1609\/aaai.v35i3.16334"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Hersche, M., Karunaratne, G., Cherubini, G., Benini, L., Sebastian, A., and Rahimi, A. (2022). Constrained few-shot class-incremental learning. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52688.2022.00885"},{"key":"ref_30","unstructured":"Yang, Y., Yuan, H., Li, X., Lin, Z., Torr, P., and Tao, D. (2022, January 25\u201329). Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental Learning. Proceedings of the Eleventh International Conference on Learning Representations, Virtual."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Park, K.H., Song, K., and Park, G.M. (2024). Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52733.2024.02254"},{"key":"ref_32","unstructured":"Yoon, I.U., Choi, T.M., Lee, S.K., Kim, Y.M., and Kim, J.H. (2023). Image-Object-Specific Prompt Learning for Few-Shot Class-Incremental Learning. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Tang, Y.M., Peng, Y.X., and Zheng, W.S. (2023). When Prompt-based Incremental Learning Does Not Meet Strong Pretraining. IEEE International Conference on Computer Vision (ICCV), IEEE.","DOI":"10.1109\/ICCV51070.2023.00164"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Jung, D., Han, D., Bang, J., and Song, H. (2023). Generating Instance-level Prompts for Rehearsal-free Continual Learning. IEEE\/CVF International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV51070.2023.01088"},{"key":"ref_35","unstructured":"Snell, J., Swersky, K., and Zemel, R. (2017). Prototypical networks for few-shot learning. Proceedings of the NeurIPS, Neural Information Processing Systems Foundation, Inc."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Wang, Q.W., Zhou, D.W., Zhang, Y.K., Zhan, D.C., and Ye, H.J. (2023). Few-Shot Class-Incremental Learning Via Training-Free Prototype Calibration. Proceedings of the NeurIPS, Neural Information Processing Systems Foundation, Inc.","DOI":"10.52202\/075280-0661"},{"key":"ref_37","unstructured":"Krizhevsky, A., and Hinton, G. (2009). Learning multiple layers of features from tiny images. 37th Conference on Neural Information Processing Systems (NeurIPS 2023), Neural Information Processing Systems Foundation, Inc."},{"key":"ref_38","unstructured":"Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., and Wierstra, D. (2016). Matching networks for one shot learning. Proceedings of the NeurPIS, Neural Information Processing Systems Foundation, Inc."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Cui, Y., Xiong, W., Tavakolian, M., and Liu, L. (2021). Semi-Supervised Few-Shot Class-Incremental Learning. Proceedings of the ICIP, IEEE.","DOI":"10.1109\/ICIP42928.2021.9506346"},{"key":"ref_40","first-page":"2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume":"Volume 1","author":"Kenton","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Zhang, C., Song, N., Lin, G., Zheng, Y., Pan, P., and Xu, Y. (2021). Few-shot incremental learning with continually evolved classifiers. Proceedings of the CVPR, IEEE.","DOI":"10.1109\/CVPR46437.2021.01227"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., and Liu, Z. (2022). Conditional prompt learning for vision-language models. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52688.2022.01631"}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/5\/407\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T12:05:55Z","timestamp":1779192355000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/5\/407"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,19]]},"references-count":42,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["a19050407"],"URL":"https:\/\/doi.org\/10.3390\/a19050407","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,19]]}}}