{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T13:34:35Z","timestamp":1790775275821,"version":"4.1.0"},"reference-count":67,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2022,4,26]],"date-time":"2022-04-26T00:00:00Z","timestamp":1650931200000},"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>In many real-life problems, it is difficult to acquire or label large amounts of data, resulting in so-called few-shot learning problems. However, few-shot classification is a challenging problem due to the uncertainty caused by using few labeled samples. In the past few years, many methods have been proposed with the common aim of transferring knowledge acquired on a previously solved task, which is often achieved by using a pretrained feature extractor. As such, if the initial task contains many labeled samples, it is possible to circumvent the limitations of few-shot learning. A shortcoming of existing methods is that they often require priors about the data distribution, such as the balance between considered classes. In this paper, we propose a novel transfer-based method with a double aim: providing state-of-the-art performance, as reported on standardized datasets in the field of few-shot learning, while not requiring such restrictive priors. Our methodology is able to cope with both inductive cases, where prediction is performed on test samples independently from each other, and transductive cases, where a joint (batch) prediction is performed.<\/jats:p>","DOI":"10.3390\/a15050147","type":"journal-article","created":{"date-parts":[[2022,4,26]],"date-time":"2022-04-26T11:45:55Z","timestamp":1650973555000},"page":"147","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":34,"title":["Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9093-1356","authenticated-orcid":false,"given":"Yuqing","family":"Hu","sequence":"first","affiliation":[{"name":"Orange S.A., F-84100 Paris, France"},{"name":"IMT Atlantique, Lab-STICC, UMR CNRS 6285, F-29238 Brest, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4345-7882","authenticated-orcid":false,"given":"St\u00e9phane","family":"Pateux","sequence":"additional","affiliation":[{"name":"Orange S.A., F-84100 Paris, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4353-4542","authenticated-orcid":false,"given":"Vincent","family":"Gripon","sequence":"additional","affiliation":[{"name":"IMT Atlantique, Lab-STICC, UMR CNRS 6285, F-29238 Brest, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,4,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Hu, Y., Gripon, V., and Pateux, S. (2021). Leveraging the feature distribution in transfer-based few-shot learning. Artificial Neural Networks and Machine Learning\u2014ICANN 2021, Proceedings of the 30th International Conference on Artificial Neural Networks, Bratislava, Slovakia, 14\u201317 September 2021, Springer.","DOI":"10.1007\/978-3-030-86340-1_39"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Mangla, P., Kumari, N., Sinha, A., Singh, M., Krishnamurthy, B., and Balasubramanian, V.N. (2020, January 1\u20135). Charting the right manifold: Manifold mixup for few-shot learning. Proceedings of the IEEE Winter Conference on Applications of Computer Vision, Snowmass Village, CO, USA.","DOI":"10.1109\/WACV45572.2020.9093338"},{"key":"ref_3","unstructured":"Wang, X., Huang, T.E., Gonzalez, J., Darrell, T., and Yu, F. (2020, January 13\u201318). Frustratingly Simple Few-Shot Object Detection. Proceedings of the 37th International Conference on Machine Learning, ICML 2020, Virtual Event."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Wang, Y., Bryan, N.J., Cartwright, M., Bello, J.P., and Salamon, J. (2021, January 6\u201311). Few-Shot Continual Learning for Audio Classification. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, Toronto, ON, Canada.","DOI":"10.1109\/ICASSP39728.2021.9413584"},{"key":"ref_5","unstructured":"Wolters, P., Careaga, C., Hutchinson, B., and Phillips, L. (2020). A Study of Few-Shot Audio Classification. arXiv."},{"key":"ref_6","unstructured":"Kubin, G., and Kacic, Z. (2019). Few-Shot Audio Classification with Attentional Graph Neural Networks. Interspeech 2019, Proceedings of the 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15\u201319 September 2019, ISCA."},{"key":"ref_7","unstructured":"Scott, D., Bel, N., and Zong, C. (2020, January 8\u201313). Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks. Proceedings of the 28th International Conference on Computational Linguistics, COLING 2020, Barcelona, Spain."},{"key":"ref_8","unstructured":"Webber, B., Cohn, T., He, Y., and Liu, Y. (2020, January 16\u201320). Self-Supervised Meta-Learning for Few-Shot Natural Language Classification Tasks. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online."},{"key":"ref_9","unstructured":"Bao, Y., Wu, M., Chang, S., and Barzilay, R. (2020, January 26\u201330). Few-shot Text Classification with Distributional Signatures. Proceedings of the 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"105067","DOI":"10.1016\/j.compbiomed.2021.105067","article-title":"Few-shot medical image segmentation using a global correlation network with discriminative embedding","volume":"140","author":"Sun","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Tang, H., Liu, X., Sun, S., Yan, X., and Xie, X. (2021, January 11\u201317). Recurrent mask refinement for few-shot medical image segmentation. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.00389"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ouyang, C., Biffi, C., Chen, C., Kart, T., Qiu, H., and Rueckert, D. (2020). Self-supervision with superpixels: Training few-shot medical image segmentation without annotation. Computer Vision\u2014ECCV 2020, Proceedings of the European Conference on Computer Vision, Glasgow, UK, 23\u201328 August 2020, Springer.","DOI":"10.1007\/978-3-030-58526-6_45"},{"key":"ref_13","unstructured":"Finn, C., Abbeel, P., and Levine, S. (2017, January 6\u201311). Model-agnostic meta-learning for fast adaptation of deep networks. Proceedings of the 34th International Conference on Machine Learning, Sydney, Australia."},{"key":"ref_14","unstructured":"Ravi, S., and Larochelle, H. (2017, January 24\u201326). Optimization as a Model for Few-Shot Learning. Proceedings of the 5th International Conference on Learning Representations, ICLR 2017, Toulon, France."},{"key":"ref_15","unstructured":"Thrun, S., and Pratt, L. (2012). Learning to Learn, Springer Science & Business Media."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Torrey, L., and Shavlik, J. (2010). Transfer learning. Handbook of Research on Machine Learning Applications and Trends: Algorithms, Methods, and Techniques, IGI Global.","DOI":"10.4018\/978-1-60566-766-9.ch011"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"3336","DOI":"10.1109\/TIP.2019.2959254","article-title":"A Two-Stage Approach to Few-Shot Learning for Image Recognition","volume":"29","author":"Das","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"ref_18","unstructured":"Chen, W., Liu, Y., Kira, Z., Wang, Y.F., and Huang, J. (2019, January 6\u20139). A Closer Look at Few-shot Classification. Proceedings of the 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Hu, Y., Gripon, V., and Pateux, S. (2021, January 10\u201315). Graph-based interpolation of feature vectors for accurate few-shot classification. Proceedings of the 2020 25th International Conference on Pattern Recognition (ICPR), Milan, Italy.","DOI":"10.1109\/ICPR48806.2021.9412076"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Lichtenstein, M., Sattigeri, P., Feris, R., Giryes, R., and Karlinsky, L. (2020). Tafssl: Task-adaptive feature sub-space learning for few-shot classification. Computer Vision\u2014ECCV 2020, Proceedings of the 16th European Conference, Glasgow, UK, 23\u201328 August 2020, Springer.","DOI":"10.1007\/978-3-030-58571-6_31"},{"key":"ref_21","unstructured":"Li, Z., Zhou, F., Chen, F., and Li, H. (2017). Meta-SGD: Learning to Learn Quickly for Few Shot Learning. arXiv."},{"key":"ref_22","unstructured":"Antoniou, A., Edwards, H., and Storkey, A.J. (2019, January 6\u20139). How to train your MAML. Proceedings of the 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA."},{"key":"ref_23","unstructured":"Bertinetto, L., Henriques, J.F., Torr, P.H.S., and Vedaldi, A. (2019, January 6\u20139). Meta-learning with differentiable closed-form solvers. Proceedings of the 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Zhang, H., Zhang, J., and Koniusz, P. (2019, January 16\u201320). Few-shot Learning via Saliency-guided Hallucination of Samples. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00288"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Chen, Z., Fu, Y., Wang, Y.X., Ma, L., Liu, W., and Hebert, M. (2019, January 16\u201320). Image deformation meta-networks for one-shot learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00888"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Mensink, T., Verbeek, J., Perronnin, F., and Csurka, G. (2012). Metric learning for large scale image classification: Generalizing to new classes at near-zero cost. Computer Vision\u2014ECCV 2012, Proceedings of the European Conference on Computer Vision, Florence, Italy, 7\u201313 October 2012, Springer.","DOI":"10.1007\/978-3-642-33709-3_35"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"542","DOI":"10.1109\/TNN.2009.2015974","article-title":"Semi-supervised learning (chapelle, o. et al., eds.; 2006) [book reviews]","volume":"20","author":"Chapelle","year":"2009","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Ye, H.J., Hu, H., Zhan, D.C., and Sha, F. (2020, January 14\u201319). Few-shot learning via embedding adaptation with set-to-set functions. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00883"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Zhang, C., Cai, Y., Lin, G., and Shen, C. (2020, January 14\u201319). DeepEMD: Few-Shot Image Classification with Differentiable Earth Mover\u2019s Distance and Structured Classifiers. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01222"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Kang, D., Kwon, H., Min, J., and Cho, M. (2021). Relational Embedding for Few-Shot Classification. arXiv.","DOI":"10.1109\/ICCV48922.2021.00870"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Rizve, M.N., Khan, S.H., Khan, F.S., and Shah, M. (2021, January 19\u201325). Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, Virtual.","DOI":"10.1109\/CVPR46437.2021.01069"},{"key":"ref_32","unstructured":"Rajasegaran, J., Khan, S.H., Hayat, M., Khan, F.S., and Shah, M. (2020). Self-supervised Knowledge Distillation for Few-shot Learning. arXiv."},{"key":"ref_33","unstructured":"Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., and Lin, H. (2020). Self-Distillation as Instance-Specific Label Smoothing. Advances in Neural Information Processing Systems 33, Proceedings of the Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, Virtual, 6\u201312 December 2020, MIT Press."},{"key":"ref_34","first-page":"266","article-title":"Rethinking Few-Shot Image Classification: A Good Embedding is All You Need?","volume":"Volume 12359","author":"Vedaldi","year":"2020","journal-title":"Computer Vision\u2014ECCV 2020, Proceedings of the 16th European Conference, Glasgow, UK, 23\u201328 August 2020"},{"key":"ref_35","unstructured":"Wang, Y., Chao, W., Weinberger, K.Q., and van der Maaten, L. (2019). SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Gripon, V., Hacene, G.B., L\u00f6we, M., and Vermet, F. (2018, January 15\u201320). Improving Accuracy of Nonparametric Transfer Learning via Vector Segmentation. Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, Canada.","DOI":"10.1109\/ICASSP.2018.8462273"},{"key":"ref_37","unstructured":"Yang, S., Liu, L., and Xu, M. (2021, January 3\u20137). Free Lunch for Few-shot Learning: Distribution Calibration. Proceedings of the 9th International Conference on Learning Representations, ICLR 2021, Virtual."},{"key":"ref_38","unstructured":"Liu, Y., Lee, J., Park, M., Kim, S., Yang, E., Hwang, S.J., and Yang, Y. (2019, January 6\u20139). Learning to Propagate Labels: Transductive Propagation Network for Few-Shot Learning. Proceedings of the 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA."},{"key":"ref_39","unstructured":"Agarap, A.F. (2018). Deep Learning using Rectified Linear Units (ReLU). arXiv."},{"key":"ref_40","unstructured":"Tukey, J.W. (1977). Exploratory Data Analysis, Springer."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1084","DOI":"10.1109\/TPAMI.2015.2484342","article-title":"Approximate fisher kernels of non-iid image models for image categorization","volume":"38","author":"Cinbis","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_42","unstructured":"Villani, C. (2008). Optimal Transport: Old and New, Springer Science & Business Media."},{"key":"ref_43","unstructured":"Cuturi, M. (2013). Sinkhorn distances: Lightspeed computation of optimal transport. Advances in Neural Information Processing Systems, MIT Press."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2766963","article-title":"Convolutional wasserstein distances: Efficient optimal transportation on geometric domains","volume":"34","author":"Solomon","year":"2015","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","article-title":"Maximum likelihood from incomplete data via the EM algorithm","volume":"39","author":"Dempster","year":"1977","journal-title":"J. R. Stat. Soc. Ser. B"},{"key":"ref_46","unstructured":"Wilson, R.C., Hancock, E.R., and Smith, W.A.P. (2016, January 19\u201322). Wide Residual Networks. Proceedings of the British Machine Vision Conference 2016, BMVC 2016, York, UK."},{"key":"ref_47","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21\u201326). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_49","unstructured":"Vinyals, O., Blundell, C., Lillicrap, T., and Wierstra, D. (2016). Matching networks for one shot learning. Advances in Neural Information Processing Systems, MIT Press."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Liu, J., Song, L., and Qin, Y. (2020). Prototype rectification for few-shot learning. Computer Vision\u2014ECCV 2020, Proceedings of the 16th European Conference, Glasgow, UK, 23\u201328 August 2020, Springer.","DOI":"10.1007\/978-3-030-58452-8_43"},{"key":"ref_51","unstructured":"Ziko, I., Dolz, J., Granger, E., and Ayed, I.B. (2020, January 12\u201318). Laplacian regularized few-shot learning. Proceedings of the International Conference on Machine Learning, Vienna, Austria."},{"key":"ref_52","unstructured":"Boudiaf, M., Ziko, I.M., Rony, J., Dolz, J., Piantanida, P., and Ayed, I.B. (2020). Transductive Information Maximization For Few-Shot Learning. arXiv."},{"key":"ref_53","unstructured":"Kye, S.M., Lee, H., Kim, H., and Hwang, S.J. (2020). Transductive Few-shot Learning with Meta-Learned Confidence. arXiv."},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Rodr\u00edguez, P., Laradji, I., Drouin, A., and Lacoste, A. (2020). Embedding propagation: Smoother manifold for few-shot classification. Computer Vision\u2014ECCV 2020, Proceedings of the European Conference on Computer Vision, Glasgow, UK, 23\u201328 August 2020, Springer.","DOI":"10.1007\/978-3-030-58574-7_8"},{"key":"ref_55","unstructured":"Snell, J., Swersky, K., and Zemel, R. (2017). Prototypical networks for few-shot learning. Advances in Neural Information Processing Systems, MIT Press."},{"key":"ref_56","unstructured":"Rusu, A.A., Rao, D., Sygnowski, J., Vinyals, O., Pascanu, R., Osindero, S., and Hadsell, R. (2019, January 6\u20139). Meta-Learning with Latent Embedding Optimization. Proceedings of the 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA."},{"key":"ref_57","unstructured":"Chobola, T., Vasata, D., and Kord\u00edk, P. (2021). Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network. arXiv."},{"key":"ref_58","doi-asserted-by":"crossref","unstructured":"Simon, C., Koniusz, P., Nock, R., and Harandi, M. (2020, January 13\u201319). Adaptive Subspaces for Few-Shot Learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00419"},{"key":"ref_59","unstructured":"Verma, V., Lamb, A., Beckham, C., Najafi, A., Mitliagkas, I., Lopez-Paz, D., and Bengio, Y. (2019, January 9\u201315). Manifold mixup: Better representations by interpolating hidden states. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_60","unstructured":"Ioffe, S., and Szegedy, C. (2015, January 6\u201311). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the International Conference on Machine Learning, Lille, France."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1093\/biomet\/58.2.341","article-title":"An omnibus test of normality for moderate and large sample sizes","volume":"58","author":"DIAgostino","year":"1971","journal-title":"Biometrika"},{"key":"ref_62","first-page":"613","article-title":"Tests for departure from normality. Empirical results for the distributions of b2 and b","volume":"60","author":"Pearson","year":"1973","journal-title":"Biometrika"},{"key":"ref_63","unstructured":"Zhang, H., Cao, Z., Yan, Z., and Zhang, C. (2021). Sill-Net: Feature Augmentation with Separated Illumination Representation. arXiv."},{"key":"ref_64","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1007\/s10994-016-5610-8","article-title":"Nearest neighbors distance ratio open-set classifier","volume":"106","author":"Werneck","year":"2017","journal-title":"Mach. Learn."},{"key":"ref_65","doi-asserted-by":"crossref","unstructured":"Bendale, A., and Boult, T.E. (2016, January 27\u201330). Towards open set deep networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.173"},{"key":"ref_66","doi-asserted-by":"crossref","unstructured":"Liu, B., Kang, H., Li, H., Hua, G., and Vasconcelos, N. (2020, January 14\u201319). Few-shot open-set recognition using meta-learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00882"},{"key":"ref_67","doi-asserted-by":"crossref","unstructured":"Jeong, M., Choi, S., and Kim, C. (2021, January 20\u201325). Few-shot Open-set Recognition by Transformation Consistency. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01238"}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/15\/5\/147\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:01:27Z","timestamp":1760137287000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/15\/5\/147"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,26]]},"references-count":67,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2022,5]]}},"alternative-id":["a15050147"],"URL":"https:\/\/doi.org\/10.3390\/a15050147","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,26]]}}}