Abstract
Most few-shot image classification methods are trained based on tasks. Usually, tasks are built on base classes with a large number of labeled images, which consumes large effort. Unsupervised few-shot image classification methods do not need labeled images, because they require tasks to be built on unlabeled images. In order to efficiently build tasks with unlabeled images, we propose a novel single-stage clustering method: Learning Features into Clustering Space (LF2CS), which first set a separable clustering space by fixing the clustering centers and then use a learnable model to learn features into the clustering space. Based on our LF2CS, we put forward an image sampling and c-way k-shot task building method. With this, we propose a novel unsupervised few-shot image classification method, which jointly learns the learnable model, clustering and few-shot image classification. Experiments and visualization show that our LF2CS has a strong ability to generalize to the novel categories. From the perspective of image sampling, we implement four baselines according to how to build tasks. We conduct experiments on the Omniglot, miniImageNet, tieredImageNet and CIFARFS datasets based on the Conv-4 and ResNet-12 backbones. Experimental results show that ours outperform the state-of-the-art methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abramson, N., Braverman, D.J., Sebestyen, G.S.: Pattern recognition and machine learning. JASA 103(482), 886–887 (2006)
Antoniou, A., Storkey, A.J.: Assume, augment and learn: Unsupervised few-shot meta-learning via random labels and data augmentation. CoRR abs/1902.09884 (2019)
Bertinetto, L., Henriques, J.F., Torr, P.H.S., Vedaldi, A.: Meta-learning with differentiable closed-form solvers. In: ICLR (2019)
Bertinetto, L., Henriques, J.F., Valmadre, J., Torr, P.H.S., Vedaldi, A.: Learning feed-forward one-shot learners. In: NIPS, pp. 523–531 (2016)
Bertugli, A., Vincenzi, S., Calderara, S., Passerini, A.: Few-shot unsupervised continual learning through meta-examples. CoRR abs/2009.08107 (2020)
Bharti, A., Balasubramanian, V.N., Jawahar, C.V.: Few shot learning with no labels. CoRR abs/2012.13751 (2020)
Caron, M., Bojanowski, P., Joulin, A., Douze, M.: Deep clustering for unsupervised learning of visual features. In: ECCV. vol. 11218, pp. 139–156 (2018)
Chen, M., et al.: Diversity transfer network for few-shot learning. In: AAAI, pp. 10559–10566 (2020)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.E.: A simple framework for contrastive learning of visual representations. In: ICML, vol. 119, pp. 1597–1607 (2020)
Cui, Y., Liu, F., Liu, X., Li, L., Qian, X.: TCSPANET: two-staged contrastive learning and sub-patch attention based network for polsar image classification. Remote Sens. 14(10), 2451 (2022)
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: ICML, vol. 70, pp. 1126–1135 (2017)
Frikha, A., Krompaß, D., Köpken, H., Tresp, V.: Few-shot one-class classification via meta-learning. In: AAAI, pp. 7448–7456 (2021)
Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations. In: ICLR (2018)
Grill, J., et al.: Bootstrap your own latent - a new approach to self-supervised learning. In: NeurIPS (2020)
He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.B.: Momentum contrast for unsupervised visual representation learning. In: CVPR, pp. 9726–9735 (2020)
Hsu, K., Levine, S., Finn, C.: Unsupervised learning via meta-learning. In: ICLR (2019)
Ji, Z., Zou, X., Huang, T., Wu, S.: Unsupervised few-shot feature learning via self-supervised training. Front. Comput. Neurosci. 14, 83 (2020)
Jiao, L., Ronghua, S., Fang, L., Weitong, Z.: Brain and Nature-Inspired Learning, Computation and Recognition. Elsevier, Amsterdam (2020)
Karypis, G., Han, E., Kumar, V.: Chameleon: Hierarchical clustering using dynamic modeling. Computer 32(8), 68–75 (1999)
Khodadadeh, S., Bölöni, L., Shah, M.: Unsupervised meta-learning for few-shot image classification. In: NeurIPS, pp. 10132–10142 (2019)
Khodadadeh, S., Zehtabian, S., Vahidian, S., Wang, W., Lin, B., Bölöni, L.: Unsupervised meta-learning through latent-space interpolation in generative models. CoRR abs/2006.10236 (2020)
Krizhevsky, A.: Learning Multiple Layers of Features from Tiny Images, pp. 32–33 (2009)
Lake, B.M., Salakhutdinov, R., Tenenbaum, J.B.: Human-level concept learning through probabilistic program induction. Science 350(6266), 1332–1338 (2015)
Lee, K., Maji, S., Ravichandran, A., Soatto, S.: Meta-learning with differentiable convex optimization. In: CVPR, pp. 10657–10665 (2019)
Li, J., Liu, G.: Few-shot image classification via contrastive self-supervised learning. arXiv abs/2008.09942 (2020)
Li, J., Wang, Z., Hu, X.: Learning intact features by erasing-inpainting for few-shot classification. In: AAAI, pp. 8401–8409 (2021)
Li, S., Liu, F., Jiao, L., Chen, P., Li, L.: Self-supervised self-organizing clustering network: a novel unsupervised representation learning method. IEEE Trans. Neural Netw. Learn. Syst. pp. 1–15 (2022)
Li, W., Xu, J., Huo, J., Wang, L., Gao, Y., Luo, J.: Distribution consistency based covariance metric networks for few-shot learning. In: AAAI, pp. 8642–8649 (2019)
Li, Z., Zhou, F., Chen, F., Li, H.: Meta-sgd: learning to learn quickly for few shot learning. CoRR abs/1707.09835 (2017)
Liu, C., Fu, Y., Xu, C., Yang, S., Li, J., Wang, C., Zhang, L.: Learning a few-shot embedding model with contrastive learning. In: AAAI, pp. 8635–8643 (2021)
Liu, F., Qian, X., Jiao, L., Zhang, X., Li, L., Cui, Y.: Contrastive learning-based dual dynamic GCN for SAR image scene classification. IEEE Trans. Neural Netw. Learn. Syst. pp. 1–15 (2022)
Lu, J., Gong, P., Ye, J., Zhang, C.: Learning from very few samples: a survey. CoRR abs/2009.02653 (2020)
Medina, C., Devos, A., Grossglauser, M.: Self-supervised prototypical transfer learning for few-shot classification. CoRR abs/2006.11325 (2020)
Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 69–84. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46466-4_5
Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: NeurIPS, pp. 8024–8035 (2019)
Qin, T., Li, W., Shi, Y., Gao, Y.: Unsupervised few-shot learning via distribution shift-based augmentation. CoRR abs/2004.05805 (2020)
Ravi, S., Larochelle, H.: Optimization as a model for few-shot learning. In: ICLR (2017)
Ren, M., et al.: Meta-learning for semi-supervised few-shot classification. In: ICLR (2018)
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015). https://doi.org/10.1007/s11263-015-0816-y
Shen, Z., Liu, Z., Qin, J., Savvides, M., Cheng, K.: Partial is better than all: revisiting fine-tuning strategy for few-shot learning. In: AAAI, pp. 9594–9602 (2021)
Snell, J., Swersky, K., Zemel, R.S.: Prototypical networks for few-shot learning. In: NIPS, pp. 4077–4087 (2017)
Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H.S., Hospedales, T.M.: Learning to compare: Relation network for few-shot learning. In: CVPR, pp. 1199–1208 (2018)
Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., Wierstra, D.: Matching networks for one shot learning. In: NIPS, pp. 3630–3638 (2016)
Wang, Y.-X., Hebert, M.: Learning to learn: model regression networks for easy small sample learning. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 616–634. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46466-4_37
Xie, J., Girshick, R.B., Farhadi, A.: Unsupervised deep embedding for clustering analysis. In: ICML, vol. 48, pp. 478–487 (2016)
Zhang, R., Isola, P., Efros, A.A.: Colorful image colorization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 649–666. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46487-9_40
Zhang, W., Jiao, L., Liu, F., Yang, S., Song, W., Liu, J.: Sparse feature clustering network for unsupervised SAR image change detection. IEEE Trans. Geosci. Remote Sens. 60, 1–13 (2022)
Zhang, X., Jiao, L., Liu, F., Bo, L., Gong, M.: Spectral clustering ensemble applied to SAR image segmentation. IEEE Trans. Geosci. Remote Sens. 46(7), 2126–2136 (2008)
Acknowledgements
This work was supported in part by the National Natural Science Foundation of China (No.62076192), Key Research and Development Program in Shaanxi Province of China (No.2019ZDLGY03-06), the State Key Program of National Natural Science of China (No.61836009), in part by the Program for Cheung Kong Scholars and Innovative Research Team in University (No. IRT_15R53), in part by The Fund for Foreign Scholars in University Research and Teaching Programs (the 111 Project) (No. B07048), in part by the Key Scientific Technological Innovation Research Project by Ministry of Education, the National Key Research and Development Program of China.
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
Li, S., Liu, F., Hao, Z., Zhao, K., Jiao, L. (2022). Unsupervised Few-Shot Image Classification by Learning Features into Clustering Space. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13691. Springer, Cham. https://doi.org/10.1007/978-3-031-19821-2_24
Download citation
DOI: https://doi.org/10.1007/978-3-031-19821-2_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19820-5
Online ISBN: 978-3-031-19821-2
eBook Packages: Computer ScienceComputer Science (R0)