Abstract
Few-shot classification aims to classify query samples using very few labeled examples. Most existing methods follow the Prototypical Network to classify query samples by matching them to the nearest centroid. However, scarce labeled examples tend to bias the centroids, which leads to query samples matching the wrong centroids. In this paper, we address the mismatching problem of centroids and query samples by optimizing the matching strategy. The idea is to combine the Shared Nearest Neighbor similarity with cosine similarity proportionally to calibrate the matching results of the latter. Furthermore, we also improve a bias-diminishing approach to increase the number of shared nearest neighbors between query samples and the centroid of their class. We validate the effectiveness of our method with extensive experiments on three few-shot classification datasets: miniImageNet, tieredImageNet, and CUB-200-2011 (CUB). Moreover, our method has achieved competitive performance across different settings and datasets.
This study is supported by the Sichuan Science and Technology Program (NO. 2021YFG0031).
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
Lake, B.M., Salakhutdinov, R., Tenenbaum, J.B.: Human-level concept learning through probabilistic program induction. Science 350(6266), 1332–1338 (2015)
Fei-Fei, L., Fergus, R., Perona, P.: One-shot learning of object categories. IEEE Trans. Pattern Anal. Mach. Intell. 28(4), 594–611 (2006)
Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., et al.: Matching networks for one shot learning. In: Advances in Neural Information Processing Systems, vol. 29 (2016)
Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Oreshkin, B., López, P.R., Lacoste, A.: TADAM: task dependent adaptive metric for improved few-shot learning. In: Advances in Neural Information Processing Systems, vol. 31 (2018)
Chen, Y., Liu, Z., Xu, H., Darrell, T., Wang, X.: Meta-baseline: exploring simple meta-learning for few-shot learning In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9062–9071 (2021)
Gao, Z., Wu, Y., Jia, Y., Harandi, M.: Curvature generation in curved spaces for few-shot learning. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8691–8700 (2021)
Wu, Y., et al.: Object-aware long-short-range spatial alignment for few-shot fine-grained image classification. arXiv preprint arXiv:2108.13098 (2021)
Wu, Z., Li, Y., Guo, L., Jia, K.: PARN: Position-aware relation networks for few-shot learning. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6659–6667 (2019)
Liu, J., Song, L., Qin, Y.: Prototype rectification for few-shot learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 741–756. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_43
Xue, W., Wang, W.: One-shot image classification by learning to restore prototypes. Proc. AAAI Conf. Artif. Intell. 34, 6558–6565 (2020)
Zhang, B., Li, X., Ye, Y., Huang, Z., Zhang, L.: 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 (2021)
Ziko, I., Dolz, J., Granger, E., Ayed, I.B.: Laplacian regularized few-shot learning. In: International Conference on Machine Learning, pp. 11660–11670. PMLR (2020)
Li, P., Gong, S., Wang, C., Fu, Y.: Ranking distance calibration for cross-domain few-shot learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9099–9108 (2022)
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning, pp. 1126–1135. PMLR (2017)
Lee, K., Maji, S., Ravichandran, A., Soatto, S.: Meta-learning with differentiable convex optimization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10-657–10-665 (2019)
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
Nichol, A., Schulman, J.: Reptile: a scalable metalearning algorithm. arXiv preprint arXiv:1803.02999, vol. 2, no. 3, p. 4 (2018)
Lee, K., Maji, S., Ravichandran, A., Soatto, S.: Meta-learning with differentiable convex optimization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10-657–10-665 (2019)
Jarvis, R.A., Patrick, E.A.: Clustering using a similarity measure based on shared near neighbors. IEEE Trans. Comput. 100(11), 1025–1034 (1973)
Bennett, K.P., Fayyad, U., Geiger, D.: Density-based indexing for approximate nearest-neighbor queries. In: Proceedings of the Fifth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 233–243 (1999)
Houle, M.E., Kriegel, H.-P., Kröger, P., Schubert, E., Zimek, A.: Can shared-neighbor distances defeat the curse of dimensionality? In: Gertz, M., Ludäscher, B. (eds.) SSDBM 2010. LNCS, vol. 6187, pp. 482–500. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-13818-8_34
Rodríguez, P., Laradji, I., Drouin, A., Lacoste, A.: Embedding propagation: smoother manifold for few-shot classification. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12371, pp. 121–138. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58574-7_8
Jiang, B., Zhao, K., Tang, J.: Rgtransformer: region-graph transformer for image representation and few-shot classification. IEEE Signal Process. Lett. 29, 792–796 (2022)
Ren, M., et al.: Meta-learning for semi-supervised few-shot classification. arXiv preprint arXiv:1803.00676 (2018)
Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD birds-200-2011 dataset (2011)
Liang, H., Zhang, Q., Dai, P., Lu, J.: Boosting the generalization capability in cross-domain few-shot learning via noise-enhanced supervised autoencoder. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9424–9434 (2021)
Guo, Y., et al.: A broader study of cross-domain few-shot learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12372, pp. 124–141. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58583-9_8
Zou, Y., Zhang, S., Chen, K., Tian, Y., Wang, Y., Moura, J.M.F.: Compositional few-shot recognition with primitive discovery and enhancing. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 156–164 (2020)
Chen, C., Yang, X., Xu, C., Huang, X., Ma, Z.: ECKPN: explicit class knowledge propagation network for transductive few-shot learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6596–6605 (2021)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Hilliard, N., Phillips, L., Howland, S., Yankov, A., Corley, C.D., Hodas, N.O.: Few-shot learning with metric-agnostic conditional embeddings. arXiv preprint arXiv:1802.04376 (2018)
Baik, S., Choi, J., Kim, H., Cho, D., Min, J., Lee, K.M.: Meta-learning with task-adaptive loss function for few-shot learning. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9465–9474 (2021)
Maniparambil, M., McGuinness, K., O’Connor, N.: Basetransformers: attention over base data-points for one shot learning. arXiv preprint arXiv:2210.02476 (2022)
Tang, S., Chen, D., Bai, L., Liu, K., Ge, Y., Ouyang, W.: Mutual CRF-GNN for few-shot learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2329–2339 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Qi, R., Ning, S., Jiang, Y., Zhang, Y., Yang, W. (2024). Shared Nearest Neighbor Calibration for Few-Shot Classification. In: Liu, Q., et al. Pattern Recognition and Computer Vision. PRCV 2023. Lecture Notes in Computer Science, vol 14428. Springer, Singapore. https://doi.org/10.1007/978-981-99-8462-6_1
Download citation
DOI: https://doi.org/10.1007/978-981-99-8462-6_1
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8461-9
Online ISBN: 978-981-99-8462-6
eBook Packages: Computer ScienceComputer Science (R0)