Abstract
Few-shot learning aims to learn a classifier that can perform well even if a few labeled samples are used for training. Many methods based on prototype models have recently been proposed and show good performance in few-shot learning. However, in the few-shot scenario, data is scarce. There is a deviation between the prototype calculated employing only a small amount of data in the support set and the actual prototype. Moreover, the features of the novel class extracted from the pre-trained model trained using base class data exhibit a bias. Additionally, the pre-trained model demonstrates high complexity and poor training efficiency. Therefore, we propose the Distributed Few-shot Learning with Prototype Distribution Correction to this end. Specifically, we employ pseudo-labels to fuse the sample features of the query set and modify the prototype to reduce the bias between the support and the query set. Then we utilize the features of the Gaussian distribution to transfer the base class features to the novel class to reduce the bias between novel classes and base classes. Finally, we combine distributed learning to improve the efficiency of the pre-trained model. We evaluate our method on Mini-ImageNet, Tiered-ImageNet, and CUB, three few-shot learning public datasets. The classification accuracy of our method improves in every case on every dataset and achieves state-of-the-art performance. In particular, the accuracy improves by 10.12% on 1-shot Mini-ImageNet.
Similar content being viewed by others
References
Byerly A, Kalganova T, Ott R (2022) The current state of the art in deep learning for image classification: a review. In: Science and information conference, pp 88–105
La Rosa B, Capobianco R, Nardi D (2023) A self-interpretable module for deep image classification on small data. Appl Intell 53(8):9115–9147
Xu C, Gao W, Li T, Bai N, Li G, Zhang Y (2023) Teacher-student collaborative knowledge distillation for image classification. Appl Intell 53(2):1997–2009
Song Y, Wang T, Cai P, Mondal SK, Sahoo JP (2023) A comprehensive survey of few-shot learning: evolution, applications, challenges, and opportunities. ACM Comput Surv
Li X, Yang X, Ma Z, Xue J-H (2023) Deep metric learning for few-shot image classification: a review of recent developments. Pattern Recognit 109381
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 1126–1135
Nichol A, Schulman J (2018) Reptile: a scalable metalearning algorithm 2(3),4. arXiv:1803.02999
Abbas M, Xiao Q, Chen L, Chen P.-Y, Chen T (2022) Sharp-maml: sharpness-aware model-agnostic meta learning. In: International conference on machine learning, PMLR, pp 10–32
Kang S, Hwang D, Eo M, Kim T, Rhee W (2023) Meta-learning with a geometry-adaptive preconditioner. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 16080–16090
Satorras VG, Estrach JB (2018) Few-shot learning with graph neural networks. In: International conference on learning representations
Kim J, Kim T, Kim S, Yoo CD (2019) Edge-labeling graph neural network for few-shot learning. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 11–20
Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. In: Advances in neural information processing systems, pp 4080–4090
Wertheimer D, Hariharan B (2019) Few-shot learning with localization in realistic settings. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 6558–6567
Li W, Wang L, Huo J, Shi Y, Gao Y, Luo J (2021) Asymmetric distribution measure for few-shot learning. In: Proceedings of the international joint conference on artificial intelligence
Li X, Wu J, Sun Z, Ma Z, Cao J, Xue J-H (2020) Bsnet: bi-similarity network for few-shot fine-grained image classification. IEEE Trans Image Process 30:1318–1331
Zhang C, Cai Y, Lin G, Shen C (2020) Deepemd: few-shot image classification with differentiable earth mover’s distance and structured classifiers. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 12203–12213
Zhou Y, Guo Y, Hao S, Hong R (2022) Hierarchical prototype refinement with progressive inter-categorical discrimination maximization for few-shot learning. IEEE Trans Image Process 31:3414–3429
Ma Y, Zhao S, Wang W, Li Y, King I (2022) Multimodality in meta-learning: a comprehensive survey. Knowl-Based Syst 250:108976
Antoniou A, Edwards H, Storkey A (2019) How to train your maml. In: International conference on learning representations
Zhang B, Li X, Ye Y, Huang Z, Zhang L (2021) Prototype completion with primitive knowledge for few-shot learning. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 3754–3762
Allen K, Shelhamer E, Shin H, Tenenbaum J (2019) Infinite mixture prototypes for few-shot learning. In: International conference on machine learning, PMLR, pp 232–241
Sergeev A, Balso MD (2018) Horovod: fast and easy distributed deep learning in tensorflow. CoRR aRxiv:1802.05799
Assran M, Loizou N, Ballas N, Rabbat M (2019) Stochastic gradient push for distributed deep learning. In: International conference on machine learning, PMLR, pp 344–353
Li S, Zhao Y, Varma R, Salpekar O, Noordhuis P, Li T, Paszke A, Smith J, Vaughan B, Damania P, Chintala S (2020) Pytorch distributed: Experiences on accelerating data parallel training. Proc VLDB Endow 13(12):3005–3018
Vinyals O, Blundell C, Lillicrap T, Kavukcuoglu K, Wierstra D (2016) Matching networks for one shot learning. In: Advances in neural information processing systems, pp 3637–3645
Mangla P, Kumari N, Sinha A, Singh M, Krishnamurthy B, Balasubramanian VN (2020) Charting the right manifold: Manifold mixup for few-shot learning. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision, pp 2218–2227
Sachin Ravi HL (2017) Optimization as a model for few-shot learning. In: International conference on learning representations
Ren M, Triantafillou E, Ravi S, Snell J, Swersky K, Tenenbaum JB, Larochelle H, Zemel RS (2018) Meta-learning for semi-supervised few-shot classification
Welinder P, Branson S, Mita T, Wah C, Schroff F, Belongie S, Perona P (2010) Caltech-ucsd birds 200
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25:1097–1105
Sung F, Yang Y, Zhang L, Xiang T, Torr PH, Hospedales TM (2018) Learning to compare: Relation network for few-shot learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1199–1208
Bertinetto L, Henriques J, Torr P, Vedaldi A (2019) Meta-learning with differentiable closed-form solvers
Liu Y, Lee J, Park M, Kim S, Yang E, Hwang S, Yang Y (2019) Learning to propagate labels: Transductive propagation network for few-shot learning. In: International conference on learning representations
Munkhdalai T, Yuan X, Mehri S, Trischler A () Rapid adaptation with conditionally shifted neurons. In: International conference on machine learning, PMLR, pp 3664–3673
Zhang R, Che T, Ghahramani Z, Bengio Y, Song Y (2018) Metagan: an adversarial approach to few-shot learning. In: Advances in neural information processing systems, pp 2371–2380
Jiang X, Havaei M, Varno F, Chartrand G, Chapados N, Matwin S (2018) Learning to learn with conditional class dependencies. In: International conference on learning representations
Qiao S, Liu C, Shen W, Yuille AL (2018) Few-shot image recognition by predicting parameters from activations. In: Proceedings of the IEEE/CVF Conference on computer vision and pattern recognition, pp 7229–7238
Rusu AA, Rao D, Sygnowski J, Vinyals O, Pascanu R, Osindero S, Hadsell R (2019) Meta-learning with latent embedding optimization
Gidaris S, Bursuc A, Komodakis N, Pérez P, Cord M (2019) Boosting few-shot visual learning with self-supervision. In:Proceedings of the IEEE/CVF international conference on computer vision, pp 8059–8068
Yang S, Liu L, Xu M (2021) Free lunch for few-shot learning: Distribution calibration. In: International conference on learning representations
Liu J, Song L, Qin Y (2020) Prototype rectification for few-shot learning. In: European conference on computer vision, pp 741–756
Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vision 115(3):211–252
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V et al (2011) Scikit-learn: Machine learning in python. J Mach Learn Res 12:2825–2830
Gidaris S, Komodakis N (2018) Dynamic few-shot visual learning without forgetting. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 4367–4375
Li H, Eigen D, Dodge S, Zeiler M, Wang X (2019) Finding task-relevant features for few-shot learning by category traversal. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 1–10
Yoon SW, Seo J, Moon J (2019) Tapnet: neural network augmented with task-adaptive projection for few-shot learning. In: International conference on machine learning, PMLR, pp 7115–7123
Sun Q, Liu Y, Chua T-S, Schiele B (2019) Meta-transfer learning for few-shot learning. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 403–412
Lee K, Maji S, Ravichandran A, Soatto S (2019) Meta-learning with differentiable convex optimization. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 10657–10665
Ravichandran A, Bhotika R, Soatto S (2019) Few-shot learning with embedded class models and shot-free meta training. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 331–339
Wang Z, Cao C, Zhu Y (2020) Entropy and confidence-based undersampling boosting random forests for imbalanced problems. IEEE Trans Neural Netw Learn Syst 31(12):5178–5191
Chen W-Y, Liu Y-C, Kira Z, Wang Y-CF, Huang J-B (2019) A closer look at few-shot classification. In: International conference on learning representations
Li W, Wang L, Xu J, Huo J, Gao Y, Luo J (2019) Revisiting local descriptor based image-to-class measure for few-shot learning. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 7260–7268
Ye H, Hu H, Zhan D, Sha F (2018) Learning embedding adaptation for few-shot learning. CoRR arXiv:1812.03664
Ziko I, Dolz J, Granger E, Ayed IB (2020) Laplacian regularized few-shot learning. In: International conference on machine learning, PMLR, pp 11660–11670
Wang Y, Chao W, Weinberger KQ, Maaten L (2019) Simpleshot: revisiting nearest-neighbor classification for few-shot learning. CoRR arXiv:1911.04623
Acknowledgements
This work is supported by Shanghai Science and Technology Program “Distributed and generative few-shot algorithm and theory research” under Grant No. 20511100600, Natural Science Foundation of China under Grant No. 62076094, Shanghai Science and Technology Program “Federated based cross-domain and cross-task incremental learning” under Grant No. 21511100800, Chinese Defense Program of Science and Technology under Grant No.2021-JCJQ-JJ-0041, China Aerospace Science and Technology Corporation Industry-University-Research Cooperation Foundation of the Eighth Research Institute under Grant No.SAST2021-007.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interest
The authors have declared no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Fu, Z., Tang, D., Ma, P. et al. Distributed few-shot learning with prototype distribution correction. Appl Intell 53, 30552–30565 (2023). https://doi.org/10.1007/s10489-023-05103-4
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-023-05103-4