{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T05:21:24Z","timestamp":1762406484576,"version":"build-2065373602"},"reference-count":46,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T00:00:00Z","timestamp":1762214400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"crossref","award":["2024JJ5649"],"award-info":[{"award-number":["2024JJ5649"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Science and Technology Innovation Program of Hunan Province","award":["2023RC3019"],"award-info":[{"award-number":["2023RC3019"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Few-Shot Class-Incremental Learning (FSCIL) aims to continually learn novel classes from limited data while retaining knowledge of previously learned classes. To mitigate catastrophic forgetting, most approaches pre-train a powerful backbone on the base session and keep it frozen during incremental sessions. Within this framework, existing studies primarily focus on representation learning in FSCIL, particularly Self-Supervised Contrastive Learning (SSCL), to enhance the transferability of representations and thereby boost model generalization to novel classes. However, they face a trade-off dilemma: improving transferability comes at the expense of discriminability, precluding simultaneous high performance on both base and novel classes. To address this issue, we propose BR-FSCIL, a representation learning framework for the FSCIL scenario. In the pre-training stage, we first design a Hierarchical Contrastive Learning (HierCon) algorithm. HierCon leverages label information to model hierarchical relationships among features. In contrast to SSCL, it maintains strong discriminability when promoting transferability. Second, to further improve the model\u2019s performance on novel classes, an Alignment Modulation (AM) loss is proposed that explicitly facilitates learning of knowledge shared across classes from an inter-class perspective. Building upon the hierarchical discriminative structure established by HierCon, it additionally improves the model\u2019s adaptability to novel classes. Through optimization at both intra-class and inter-class levels, the representations learned by BR-FSCIL achieve a balance between discriminability and transferability. Extensive experiments on mini-ImageNet, CIFAR100, and CUB200 demonstrate the effectiveness of our method, which achieves final session accuracies of 53.83%, 53.04%, and 62.60%, respectively.<\/jats:p>","DOI":"10.3390\/jimaging11110391","type":"journal-article","created":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T12:13:08Z","timestamp":1762258388000},"page":"391","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Pursuing Better Representations: Balancing Discriminability and Transferability for Few-Shot Class-Incremental Learning"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3027-0465","authenticated-orcid":false,"given":"Qi","family":"Li","sequence":"first","affiliation":[{"name":"National Key Laboratory of Automatic Target Recognition, College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Automatic Target Recognition, College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Fan","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence Application, Central South University of Forestry and Technology, Changsha 410004, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingwei","family":"Hui","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Automatic Target Recognition, College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Information Science and Electronic Engineering, Shanghai Jiao Tong University, Shanghai 200240, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,4]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Valente, J., Ant\u00f3nio, J., Mora, C., and Jardim, S. (2023). Developments in image processing using deep learning and reinforcement learning. J. Imaging, 9.","DOI":"10.3390\/jimaging9100207"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Fei-Fei, L. (2009, January 20\u201325). Imagenet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami Beach, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Man, K., and Chahl, J. (2022). A review of synthetic image data and its use in computer vision. J. Imaging, 8.","DOI":"10.3390\/jimaging8110310"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Wu, Y., Chen, Y., Wang, L., Ye, Y., Liu, Z., Guo, Y., and Fu, Y. (2019, January 16\u201320). Large scale incremental learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00046"},{"key":"ref_6","unstructured":"Zhou, D.W., Wang, Q.W., Qi, Z.H., Ye, H.J., Zhan, D.C., and Liu, Z. (2023). Deep class-incremental learning: A survey. arXiv."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"9650","DOI":"10.1109\/TCSVT.2025.3562603","article-title":"Few-Shot Class-Incremental Learning via Asymmetric Supervised Contrastive Learning","volume":"35","author":"Liu","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Tao, X., Hong, X., Chang, X., Dong, S., Wei, X., and Gong, Y. (2020, January 14\u201319). Few-shot class-incremental learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01220"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1576","DOI":"10.1109\/TPAMI.2021.3133897","article-title":"MgSvF: Multi-Grained Slow versus Fast Framework for Few-Shot Class-Incremental Learning","volume":"46","author":"Zhao","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Mazumder, P., Singh, P., and Rai, P. (2021, January 2\u20139). Few-shot lifelong learning. Proceedings of the AAAI Conference on Artificial Intelligence, Online.","DOI":"10.1609\/aaai.v35i3.16334"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zhang, C., Song, N., Lin, G., Zheng, Y., Pan, P., and Xu, Y. (2021, January 19\u201325). Few-shot incremental learning with continually evolved classifiers. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Online.","DOI":"10.1109\/CVPR46437.2021.01227"},{"key":"ref_12","unstructured":"Graf, F., Hofer, C., Niethammer, M., and Kwitt, R. (2021, January 18\u201324). Dissecting supervised contrastive learning. Proceedings of the International Conference on Machine Learning, Online."},{"key":"ref_13","first-page":"6827","article-title":"What makes for good views for contrastive learning?","volume":"33","author":"Tian","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Jaiswal, A., Babu, A.R., Zadeh, M.Z., Banerjee, D., and Makedon, F. (2020). A survey on contrastive self-supervised learning. Technologies, 9.","DOI":"10.3390\/technologies9010002"},{"key":"ref_15","unstructured":"Chen, M., Fu, D.Y., Narayan, A., Zhang, M., Song, Z., Fatahalian, K., and R\u00e9, C. (2022, January 17\u201323). Perfectly balanced: Improving transfer and robustness of supervised contrastive learning. Proceedings of the International Conference on Machine Learning, Baltimore, MD, USA."},{"key":"ref_16","unstructured":"Oh, J., Baik, S., and Lee, K.M. (October, January 29). Closer: Towards better representation learning for few-shot class-incremental learning. Proceedings of the European Conference on Computer Vision, Milan, Italy."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2624","DOI":"10.1109\/TPAMI.2013.83","article-title":"Distance-based image classification: Generalizing to new classes at near-zero cost","volume":"35","author":"Mensink","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_18","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_19","doi-asserted-by":"crossref","first-page":"5921","DOI":"10.1109\/TCSVT.2023.3262739","article-title":"Semantic knowledge guided class-incremental learning","volume":"33","author":"Wang","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Rebuffi, S.A., Kolesnikov, A., Sperl, G., and Lampert, C.H. (2017, January 21\u201326). icarl: Incremental classifier and representation learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2217","DOI":"10.1109\/TCSVT.2022.3219605","article-title":"Anchor assisted experience replay for online class-incremental learning","volume":"33","author":"Lin","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_22","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_23","doi-asserted-by":"crossref","unstructured":"Castro, F.M., Mar\u00edn-Jim\u00e9nez, M.J., Guil, N., Schmid, C., and Alahari, K. (2018, January 8\u201314). End-to-end incremental learning. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01258-8_15"},{"key":"ref_24","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1089","DOI":"10.1109\/TPAMI.2024.3492328","article-title":"Language-inspired relation transfer for few-shot class-incremental learning","volume":"47","author":"Zhao","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zhou, D.W., Wang, F.Y., Ye, H.J., Ma, L., Pu, S., and Zhan, D.C. (2022, January 19\u201324). Forward compatible few-shot class-incremental learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00884"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Song, Z., Zhao, Y., Shi, Y., Peng, P., Yuan, L., and Tian, Y. (2023, January 18\u201322). Learning with fantasy: Semantic-aware virtual contrastive constraint for few-shot class-incremental learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.02316"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"14975","DOI":"10.1109\/TNNLS.2025.3548465","article-title":"BFCP: Pursue Better Forward Compatibility Pretraining for Few-Shot Class-Incremental Learning","volume":"36","author":"Fu","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Islam, A., Chen, C.F.R., Panda, R., Karlinsky, L., Radke, R., and Feris, R. (2021, January 19\u201325). A broad study on the transferability of visual representations with contrastive learning. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Online.","DOI":"10.1109\/ICCV48922.2021.00872"},{"key":"ref_30","first-page":"27267","article-title":"Margin-based few-shot class-incremental learning with class-level overfitting mitigation","volume":"35","author":"Zou","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_31","first-page":"18661","article-title":"Supervised contrastive learning","volume":"33","author":"Khosla","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_32","unstructured":"Chen, T., Kornblith, S., Norouzi, M., and Hinton, G. (2020, January 12\u201318). A simple framework for contrastive learning of visual representations. Proceedings of the International Conference on Machine Learning, Vienna, Austria."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., and Girshick, R. (2020, January 14\u201319). Momentum contrast for unsupervised visual representation learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Online.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., and Zafeiriou, S. (2019, January 16\u201320). Arcface: Additive angular margin loss for deep face recognition. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref_35","unstructured":"Oord, A.v.d., Li, Y., and Vinyals, O. (2018). Representation learning with contrastive predictive coding. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Bau, D., Zhou, B., Khosla, A., Oliva, A., and Torralba, A. (2017, January 21\u201326). Network dissection: Quantifying interpretability of deep visual representations. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.354"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., and Torralba, A. (2016, January 27\u201330). Learning deep features for discriminative localization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Zou, Y., Zhang, S., Chen, K., Tian, Y., Wang, Y., and Moura, J.M. (2020, January 12\u201316). Compositional few-shot recognition with primitive discovery and enhancing. Proceedings of the 28th ACM International Conference on Multimedia, Online.","DOI":"10.1145\/3394171.3413849"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"Imagenet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"ref_40","unstructured":"Krizhevsky, A., and Hinton, G. (2009). Learning Multiple Layers of Features from Tiny Images, University of Toronto."},{"key":"ref_41","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., and Belongie, S. (2025, September 20). The Caltech-Ucsd Birds-200-2011 Dataset. Available online: https:\/\/www.vision.caltech.edu\/datasets\/cub_200_2011\/."},{"key":"ref_42","unstructured":"Kang, H., Yoon, J., Madjid, S.R.H., Hwang, S.J., and Yoo, C.D. (2022). On the soft-subnetwork for few-shot class incremental learning. arXiv."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"14259","DOI":"10.1109\/TNNLS.2023.3277018","article-title":"Uncertainty-aware distillation for semi-supervised few-shot class-incremental learning","volume":"35","author":"Cui","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"13417","DOI":"10.1109\/TNNLS.2024.3454237","article-title":"Brain-inspired fast-and slow-update prompt tuning for few-shot class-incremental learning","volume":"36","author":"Ran","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-cam: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"McInnes, L., Healy, J., and Melville, J. (2018). Umap: Uniform manifold approximation and projection for dimension reduction. arXiv.","DOI":"10.21105\/joss.00861"}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/11\/11\/391\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T05:17:38Z","timestamp":1762406258000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/11\/11\/391"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,4]]},"references-count":46,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["jimaging11110391"],"URL":"https:\/\/doi.org\/10.3390\/jimaging11110391","relation":{},"ISSN":["2313-433X"],"issn-type":[{"type":"electronic","value":"2313-433X"}],"subject":[],"published":{"date-parts":[[2025,11,4]]}}}