Abstract
Few-shot learners aim to recognize new categories given only a small number of training samples. The core challenge is to avoid overfitting to the limited data while ensuring good generalization to novel classes. Existing literature makes use of vast amounts of annotated data by simply shifting the label requirement from novel classes to base classes. Since data annotation is time-consuming and costly, reducing the label requirement even further is an important goal. To that end, our paper presents a more challenging few-shot setting with almost no class label access. By leveraging self-supervision to learn image representations and similarity for classification at test time, we achieve competitive baselines while using almost zero (0–5) class labels. Compared to existing state-of-the-art approaches which use 60,000 labels, this is a four orders of magnitude (10,000 times) difference. This work is a step towards developing few-shot learning methods that do not depend on annotated data. Our code is publicly released at https://github.com/adbugger/FewShot. (This work was supported by the IMPRINT program.)
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Antoniou, A., Edwards, H., Storkey, A.: How to train your MAML. In: ICLR (2019)
Antoniou, A., Storkey, A.: Assume, augment and learn: unsupervised few-shot meta-learning via random labels and data augmentation. In: ICML (2019)
Bertinetto, L., Henriques, J.F., Torr, P., Vedaldi, A.: Meta-learning with differentiable closed-form solvers. In: ICLR (2019)
Chen, D., Chen, Y., Li, Y., Mao, F., He, Y., Xue, H.: Self-supervised learning for few-shot image classification (2019)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML (2020)
Chen, W.Y., Liu, Y.C., Kira, Z., Wang, Y.C., Huang, J.B.: A closer look at few-shot classification. In: ICLR (2019)
Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning (2020). arXiv preprint arXiv:2003.04297
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)
Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context prediction. In: ICCV (2015)
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: ICML (2017)
Finn, C., Xu, K., Levine, S.: Probabilistic model-agnostic meta-learning. In: NeurIPS (2018)
Gidaris, S., Bursuc, A., Komodakis, N., Pérez, P.P., Cord, M.: Boosting few-shot visual learning with self-supervision. In: ICCV (2019)
Gidaris, S., Komodakis, N.: Dynamic few-shot visual learning without forgetting. In: CVPR (2018)
Gidaris, S., Bursuc, A., Komodakis, N., Pérez, P., Cord, M.: Learning representations by predicting bags of visual words. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6928–6938 (2020)
Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations. In: ICLR (2018)
Grant, E., Finn, C., Levine, S., Darrell, T., Griffiths, T.: Recasting gradient-based meta-learning as hierarchical bayes (2018). arXiv preprint arXiv:1801.08930
Hariharan, B., Girshick, R.: Low-shot visual recognition by shrinking and hallucinating features. In: ICCV (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR (2020)
Horn, G.V., Perona, P.: The devil is in the tails: fine-grained classification in the wild (2017). CoRR abs/1709.01450, http://arxiv.org/abs/1709.01450
Ji, X., Henriques, J.F., Vedaldi, A.: Invariant information clustering for unsupervised image classification and segmentation. In: ICCV (2019)
Koch, G., Zemel, R., Salakhutdinov, R.: Siamese neural networks for one-shot image recognition. In: ICML-W (2015)
Krizhevsky, A.: Learning multiple layers of features from tiny images. University of Toronto (2009)
Larsson, G., Maire, M., Shakhnarovich, G.: Learning representations for automatic colorization. In: ECCV (2016)
Lee, K., Maji, S., Ravichandran, A., Soatto, S.: Meta-learning with differentiable convex optimization. In: CVPR (2019)
Mangla, P., Kumari, N., Sinha, A., Singh, M., Krishnamurthy, B., Balasubramanian, V.N.: Charting the right manifold: manifold mixup for few-shot learning. In: WACV (2020)
Nguyen, C., Do, T.T., Carneiro, G.: Uncertainty in model-agnostic meta-learning using variational inference. In: WACV (2020)
Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles. In: ECCV (2016)
Oreshkin, B., Rodríguez López, P., Lacoste, A.: Tadam: Task dependent adaptive metric for improved few-shot learning. In: NeurIPS (2018)
Ravi, S., Larochelle, H.: Optimization as a model for few-shot learning. In: ICLR (2017)
Rusu, A.A., et al.: Meta-learning with latent embedding optimization. In: ICLR (2019)
Satorras, V.G., Estrach, J.B.: Few-shot learning with graph neural networks. In: ICLR (2018)
Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: NeurIPS (2017)
Su, J.C., Maji, S., Hariharan, B.: Boosting supervision with self-supervision for few-shot learning (2019). ArXiv abs/1906.07079
Sun, Q., Liu, Y., Chua, T.S., Schiele, B.: Meta-transfer learning for few-shot learning. In: CVPR (2019)
Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H., Hospedales, T.M.: Learning to compare: relation network for few-shot learning. In: CVPR (2018)
Tian, Y., Krishnan, D., Isola, P.: Contrastive multiview coding (2019). arXiv preprint arXiv:1906.05849
Tian, Y., Wang, Y., Krishnan, D., Tenenbaum, J.B., Isola, P.: Rethinking few-shot image classification: a good embedding is all you need? In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 266–282. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58568-6_16
Vinyals, O., Blundell, C., Lillicrap, T., kavukcuoglu, k., Wierstra, D.: Matching networks for one shot learning. In: NeurIPS (2016)
Wang, Y., Chao, W.L., Weinberger, K.Q., van der Maaten, L.: Simpleshot: Revisiting nearest-neighbor classification for few-shot learning (2019)
Wang, Y., Yao, Q., Kwok, J.T., Ni, L.M.: Generalizing from a few examples: a survey on few-shot learning. ACM Comput. Surv. (CSUR) 53(3), 1–34 (2019)
Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: CVPR, pp. 3733–3742 (2018)
Yoon, J., Kim, T., Dia, O., Kim, S., Bengio, Y., Ahn, S.: Bayesian model-agnostic meta-learning. In: NeurIPS (2018)
Zhang, R., Isola, P., Efros, A.A.: Colorful image colorization. In: ECCV (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Bharti, A., Vineeth, N.B., Jawahar, C.V. (2022). Towards Label-Free Few-Shot Learning: How Far Can We Go?. In: Raman, B., Murala, S., Chowdhury, A., Dhall, A., Goyal, P. (eds) Computer Vision and Image Processing. CVIP 2021. Communications in Computer and Information Science, vol 1567. Springer, Cham. https://doi.org/10.1007/978-3-031-11346-8_23
Download citation
DOI: https://doi.org/10.1007/978-3-031-11346-8_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-11345-1
Online ISBN: 978-3-031-11346-8
eBook Packages: Computer ScienceComputer Science (R0)