{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T05:31:19Z","timestamp":1766467879586},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T00:00:00Z","timestamp":1715126400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T00:00:00Z","timestamp":1715126400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Few-shot class-incremental learning (FSCIL) struggles to incrementally recognize novel classes from few examples without catastrophic forgetting of old classes or overfitting to new classes. We propose TLCE, which ensembles multiple pre-trained models to improve separation of novel and old classes. Specifically, we use episodic training to map images from old classes to quasi-orthogonal prototypes, which minimizes interference between old and new classes. Then, we incorporate the use of ensembling diverse pre-trained models to further tackle the challenge of data imbalance and enhance adaptation to novel classes. Extensive experiments on various datasets demonstrate that our transfer learning ensemble approach outperforms state-of-the-art FSCIL methods.<\/jats:p>","DOI":"10.1007\/s11063-024-11605-0","type":"journal-article","created":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T04:01:38Z","timestamp":1715140898000},"update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["TLCE: Transfer-Learning Based Classifier Ensembles for Few-Shot Class-Incremental Learning"],"prefix":"10.1007","volume":"56","author":[{"given":"Shuangmei","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tieru","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,5,8]]},"reference":[{"key":"11605_CR1","doi-asserted-by":"crossref","unstructured":"Hersche M, Karunaratne G, Cherubini G, Benini L, Sebastian A, Rahimi A (2022)Constrained few-shot class-incremental learning. In: IEEE\/CVF conference on computer vision and pattern recognition, pp 9057\u20139067","DOI":"10.1109\/CVPR52688.2022.00885"},{"key":"11605_CR2","doi-asserted-by":"crossref","unstructured":"Zhu K, Cao Y, Zhai W, Cheng J, Zha Z-J (2021) Self-promoted prototype refinement for few-shot class-incremental learning. In: IEEE\/CVF conference on computer vision and pattern recognition, pp 6801\u20136810","DOI":"10.1109\/CVPR46437.2021.00673"},{"key":"11605_CR3","doi-asserted-by":"crossref","unstructured":"Zhang C, Song N, Lin G, Zheng Y, Pan P, Xu Y (2021) Few-shot incremental learning with continually evolved classifiers. In: IEEE\/CVF conference on computer vision and pattern recognition, pp 12455\u201312464","DOI":"10.1109\/CVPR46437.2021.01227"},{"key":"11605_CR4","first-page":"6747","volume":"34","author":"G Shi","year":"2021","unstructured":"Shi G, Chen J, Zhang W, Zhan L-M, Wu X-M (2021) Overcoming catastrophic forgetting in incremental few-shot learning by finding flat minima. Adv Neural Inf Process Syst 34:6747\u20136761","journal-title":"Adv Neural Inf Process Syst"},{"key":"11605_CR5","unstructured":"Chen W-Y, Liu Y-C, Kira Z, Wang Y-CF, Huang J-B (2019) A Closer Look at Few-shot Classification. In: The international conference on learning representations"},{"key":"11605_CR6","doi-asserted-by":"crossref","unstructured":"Tian Y, Wang Y, Krishnan D, Tenenbaum JB, Isola P (2020) Rethinking few-shot image classification: a good embedding is all you need? In: The European conference on computer vision, Springer, pp 266\u2013282","DOI":"10.1007\/978-3-030-58568-6_16"},{"issue":"3","key":"11605_CR7","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211\u2013252","journal-title":"Int J Comput Vis"},{"key":"11605_CR8","volume-title":"Handbook of systemic autoimmune diseases","author":"A Krizhevsky","year":"2009","unstructured":"Krizhevsky A, Hinton G et al (2009) Learning multiple layers of features from tiny images. Handbook of systemic autoimmune diseases, vol 1. University of Toronto, Toronto"},{"issue":"9","key":"11605_CR9","first-page":"5149","volume":"44","author":"T Hospedales","year":"2021","unstructured":"Hospedales T, Antoniou A, Micaelli P, Storkey A (2021) Meta-learning in neural networks: a survey. IEEE Trans Pattern Anal Mach Intell 44(9):5149\u20135169","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11605_CR10","unstructured":"Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In: International conference on machine learning, PMLR, pp 1126\u20131135"},{"key":"11605_CR11","doi-asserted-by":"crossref","unstructured":"Jamal MA, Qi G-J (2019) Task agnostic meta-learning for few-shot learning. In: IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2019.01199"},{"key":"11605_CR12","unstructured":"Rusu AA, Rao D, Sygnowski J, Vinyals O, Pascanu R, Osindero S, Hadsell R (2019) Meta-learning with latent embedding optimization. In: The international conference on learning representations"},{"key":"11605_CR13","unstructured":"Koch G, Zemel R, Salakhutdinov R (2015) Siamese neural networks for one-shot image recognition. In: The international conference on machine learning. Deep learning workshop"},{"key":"11605_CR14","unstructured":"Vinyals O, Blundell C, Lillicrap T, Wierstra D et al (2016) Matching networks for one shot learning. In: Advances in neural information processing systems, vol 29"},{"key":"11605_CR15","unstructured":"Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. In: Advances in neural information processing systems, vol 30"},{"key":"11605_CR16","doi-asserted-by":"crossref","unstructured":"Sung F, Yang Y, Zhang L, Xiang T, Torr PH, Hospedales TM (2018) Learning to compare: relation network for few-shot learning. In: IEEE conference on computer vision and pattern recognition, pp 1199\u20131208","DOI":"10.1109\/CVPR.2018.00131"},{"key":"11605_CR17","unstructured":"Yang S, Liu L, Xu M (2021) Free lunch for few-shot learning: distribution calibration. In: The international conference on learning representations"},{"key":"11605_CR18","doi-asserted-by":"publisher","first-page":"4543","DOI":"10.1109\/TIP.2022.3184813","volume":"31","author":"Y Guo","year":"2022","unstructured":"Guo Y, Du R, Li X, Xie J, Ma Z, Dong Y (2022) Learning calibrated class centers for few-shot classification by pair-wise similarity. IEEE Trans Image Process 31:4543\u20134555","journal-title":"IEEE Trans Image Process"},{"key":"11605_CR19","unstructured":"Xu J, Luo X, Pan X, Pei W, Li Y, Xu Z (2022) Alleviating the sample selection bias in few-shot learning by removing projection to the centroid. In: Advances in neural information processing systems"},{"key":"11605_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2023.104736","volume":"136","author":"S Wang","year":"2023","unstructured":"Wang S, Ma R, Wu T, Cao Y (2023) P3dc-shot: prior-driven discrete data calibration for nearest-neighbor few-shot classification. Image Vis Comput 136:104736","journal-title":"Image Vis Comput"},{"key":"11605_CR21","doi-asserted-by":"crossref","unstructured":"Iscen A, Zhang J, Lazebnik S, Schmid C (2020) Memory-efficient incremental learning through feature adaptation. In: The European conference on computer vision, Springer, pp 699\u2013715","DOI":"10.1007\/978-3-030-58517-4_41"},{"key":"11605_CR22","doi-asserted-by":"crossref","unstructured":"Zhu F, Zhang X-Y, Wang C, Yin F, Liu C-L (2021) Prototype augmentation and self-supervision for incremental learning. In: IEEE conference on computer vision and pattern recognition, pp 5871\u20135880","DOI":"10.1109\/CVPR46437.2021.00581"},{"key":"11605_CR23","doi-asserted-by":"crossref","unstructured":"Petit G, Popescu A, Schindler H, Picard D, Delezoide B (2023) Fetril: feature translation for exemplar-free class-incremental learning. In: IEEE Winter Conference on Applications of Computer Vision, pp 3911\u20133920","DOI":"10.1109\/WACV56688.2023.00390"},{"issue":"13","key":"11605_CR24","doi-asserted-by":"publisher","first-page":"3521","DOI":"10.1073\/pnas.1611835114","volume":"114","author":"J Kirkpatrick","year":"2017","unstructured":"Kirkpatrick J, Pascanu R, Rabinowitz N, Veness J, Desjardins G, Rusu AA, Milan K, Quan J, Ramalho T, Grabska-Barwinska A (2017) Overcoming catastrophic forgetting in neural networks. Proc Natl Acad Sci 114(13):3521\u20133526","journal-title":"Proc Natl Acad Sci"},{"key":"11605_CR25","doi-asserted-by":"crossref","unstructured":"Chaudhry A, Dokania PK, Ajanthan T, Torr PH (2018) Riemannian walk for incremental learning: understanding forgetting and intransigence. In: The European conference on computer vision, pp 532\u2013547","DOI":"10.1007\/978-3-030-01252-6_33"},{"key":"11605_CR26","doi-asserted-by":"crossref","unstructured":"Lee J, Hong HG, Joo D, Kim J (2020) Continual learning with extended kronecker-factored approximate curvature. In: IEEE conference on computer vision and pattern recognition, pp 9001\u20139010","DOI":"10.1109\/CVPR42600.2020.00902"},{"key":"11605_CR27","doi-asserted-by":"crossref","unstructured":"Rebuffi S-A, Kolesnikov A, Sperl G, Lampert CH (2017) icarl: incremental classifier and representation learning. In: IEEE conference on computer vision and pattern recognition, pp 2001\u20132010","DOI":"10.1109\/CVPR.2017.587"},{"key":"11605_CR28","doi-asserted-by":"crossref","unstructured":"Castro FM, Marin-Jimenez MJ, Guil N, Schmid C, Alahari K (2018) End-to-end incremental learning. In: The European conference on computer vision","DOI":"10.1007\/978-3-030-01258-8_15"},{"key":"11605_CR29","doi-asserted-by":"crossref","unstructured":"Gao Q, Zhao C, Ghanem B, Zhang J (2022) R-dfcil: relation-guided representation learning for data-free class incremental learning. In: The European conference on computer vision, Springer, pp 423\u2013439","DOI":"10.1007\/978-3-031-20050-2_25"},{"key":"11605_CR30","doi-asserted-by":"crossref","unstructured":"Yu L, Twardowski B, Liu X, Herranz L, Wang K, Cheng Y, Jui S, Weijer JVD (2020) Semantic drift compensation for class-incremental learning. In: IEEE conference on computer vision and pattern recognition, pp 6982\u20136991","DOI":"10.1109\/CVPR42600.2020.00701"},{"key":"11605_CR31","doi-asserted-by":"crossref","unstructured":"Liu Y, Schiele B, Sun Q (2021) Adaptive aggregation networks for class-incremental learning. In: The European conference on computer vision, pp 2544\u20132553","DOI":"10.1109\/CVPR46437.2021.00257"},{"key":"11605_CR32","doi-asserted-by":"publisher","unstructured":"Tao X, Hong X, Chang X, Dong S, Wei X, Gong Y (2020) Few-shot class-incremental learning. In: IEEE conference on computer vision and pattern recognition, pp 12180\u201312189 . https:\/\/doi.org\/10.1109\/CVPR42600.2020.01220","DOI":"10.1109\/CVPR42600.2020.01220"},{"key":"11605_CR33","doi-asserted-by":"crossref","unstructured":"Cheraghian A, Rahman S, Fang P, Roy SK, Petersson L, Harandi M (2021) Semantic-aware knowledge distillation for few-shot class-incremental learning. In: IEEE conference on computer vision and pattern recognition, pp 2534\u20132543","DOI":"10.1109\/CVPR46437.2021.00256"},{"key":"11605_CR34","doi-asserted-by":"crossref","unstructured":"Dong S, Hong X, Tao X, Chang X, Wei X, Gong Y (2021) Few-shot class-incremental learning via relation knowledge distillation. In: AAAI conference on artificial intelligence, vol 35, pp 1255\u20131263","DOI":"10.1609\/aaai.v35i2.16213"},{"key":"11605_CR35","doi-asserted-by":"crossref","unstructured":"Zhou D-W, Wang F-Y, Ye H-J, Ma L, Pu S, Zhan D-C (2022) Forward compatible few-shot class-incremental learning. In: IEEE conference on computer vision and pattern recognition, pp 9046\u20139056","DOI":"10.1109\/CVPR52688.2022.00884"},{"key":"11605_CR36","doi-asserted-by":"crossref","unstructured":"Peng C, Zhao K, Wang T, Li M, Lovell BC (2022) Few-shot class-incremental learning from an open-set perspective. In: The European conference on computer vision, Springer, pp 382\u2013397","DOI":"10.1007\/978-3-031-19806-9_22"},{"key":"11605_CR37","doi-asserted-by":"crossref","unstructured":"Song Z, Zhao Y, Shi Y, Peng P, Yuan L, Tian Y (2023) Learning with fantasy: semantic-aware virtual contrastive constraint for few-shot class-incremental learning. In: IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR52729.2023.02316"},{"key":"11605_CR38","unstructured":"Kim D-Y, Han D-J, Seo J, Moon J (2023) Warping the space: weight space rotation for class-incremental few-shot learning. In: The international conference on learning representations"},{"key":"11605_CR39","doi-asserted-by":"crossref","unstructured":"Mazumder P, Singh P, Rai P (2021) Few-shot lifelong learning. In: AAAI conference on artificial intelligence, vol 35, pp 2337\u20132345","DOI":"10.1609\/aaai.v35i3.16334"},{"key":"11605_CR40","doi-asserted-by":"crossref","unstructured":"Chi Z, Gu L, Liu H, Wang Y, Yu Y, Tang J (2022) Metafscil: a meta-learning approach for few-shot class incremental learning. In: IEEE conference on computer vision and pattern recognition, pp 14166\u201314175","DOI":"10.1109\/CVPR52688.2022.01377"},{"key":"11605_CR41","doi-asserted-by":"publisher","first-page":"937","DOI":"10.1109\/TIP.2023.3236160","volume":"32","author":"Z Ji","year":"2023","unstructured":"Ji Z, Hou Z, Liu X, Pang Y, Li X (2023) Memorizing complementation network for few-shot class-incremental learning. IEEE Trans Image Process 32:937\u2013948","journal-title":"IEEE Trans Image Process"},{"issue":"15","key":"11605_CR42","doi-asserted-by":"publisher","first-page":"10875","DOI":"10.1007\/s00521-023-08272-y","volume":"35","author":"X Xu","year":"2023","unstructured":"Xu X, Wang Z, Fu Z, Guo W, Chi Z, Li D (2023) Flexible few-shot class-incremental learning with prototype container. Neural Comput Appl 35(15):10875\u201310889","journal-title":"Neural Comput Appl"},{"issue":"1","key":"11605_CR43","doi-asserted-by":"publisher","first-page":"2468","DOI":"10.1038\/s41467-021-22364-0","volume":"12","author":"G Karunaratne","year":"2021","unstructured":"Karunaratne G, Schmuck M, Le Gallo M, Cherubini G, Benini L, Sebastian A, Rahimi A (2021) Robust high-dimensional memory-augmented neural networks. Nat Commun 12(1):2468","journal-title":"Nat Commun"},{"key":"11605_CR44","unstructured":"Lesort, T, George T, Rish I (2021) Continual learning in deep networks: an analysis of the last layer. arXiv preprint arXiv:2106.01834"},{"key":"11605_CR45","unstructured":"Wang Y, Chao W-L, Weinberger KQ, Maaten L (2019) Simpleshot: revisiting nearest-neighbor classification for few-shot learning. arXiv preprint arXiv:1911.04623"},{"key":"11605_CR46","doi-asserted-by":"crossref","unstructured":"Hou S, Pan X, Loy CC, Wang Z, Lin D (2019) Learning a unified classifier incrementally via rebalancing. In: IEEE conference on computer vision and pattern recognition, pp 831\u2013839","DOI":"10.1109\/CVPR.2019.00092"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-024-11605-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-024-11605-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-024-11605-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T11:19:22Z","timestamp":1721042362000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-024-11605-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,8]]},"references-count":46,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,6]]}},"alternative-id":["11605"],"URL":"https:\/\/doi.org\/10.1007\/s11063-024-11605-0","relation":{},"ISSN":["1573-773X"],"issn-type":[{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,8]]},"assertion":[{"value":"18 March 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 May 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare to have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"167"}}