Abstract
Few-shot learning, which aims to classify unknown categories with fewer label samples, has become a research hotspot in computer vision because of its wide application. Objects will present different regional locations in nature, and the existing few-shot learning only focuses on the overall location information, while ignoring the impact of local key information on classification tasks. To solve this problem, (1) we propose a new multi-scale adaptive region attention network (MARANet), which makes use of the semantic similarity between images to make the model pay more attention to the areas that are beneficial to the classification task. (2) MARANet mainly includes two modules—the multi-scale feature generation module uses low-level features (LF) of different scales to solve the problem of different target scales in nature; the adaptive region metric module selects the LF of key regions by assigning masks to each classification task. We have conducted experiments on three common data sets (i.e. miniImageNet, CUB-200, and Stanford Cars). The experimental results show that the new category classification task of MARANet is \(1.1\%\sim 4.9\%\) higher than the existing methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abdelaziz, M., Zhang, Z.: Multi-scale Kronecker-product relation networks for few-shot learning. Multimed. Tools. Appl. 81(5), 6703–6722 (2022)
Afrasiyabi, A., Lalonde, J.-F., Gagné, C.: Mixture-based feature space learning for few-shot image classification. In: ICCV, pp. 9041–9051 (2021)
Baik, S., Hong, S., Lee, K.M.: Learning to forget for meta-learning. In: CVPR, pp. 2379–2387 (2020)
Deleu, T., et al.: Continuous-time meta-learning with forward mode differentiation. arXiv preprint arXiv:2203.01443 (2022)
Dhillon, G.S., Chaudhari, P., Ravichandran, A., Soatto, S.: A baseline for few-shot image classification. arXiv preprint arXiv:1909.02729 (2019)
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: ICML, pp. 1126–1135 (2017)
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: ICLR, pp. 1126–1135 (2017)
Flennerhag, S., Schroecker, Y., Zahavy, T., van Hasselt, H., Silver, D., Singh, S.: Bootstrapped meta-learning. arXiv preprint arXiv:2109.04504 (2021)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: ICCVW, pp. 554–561 (2013)
Lee, K., Maji, S., Ravichandran, A., Soatto, S.: Meta-learning with differentiable convex optimization. In: CVPR, pp. 10657–10665 (2019)
Li, H., Eigen, D., Dodge, S., Zeiler, M., Wang, X.: Finding task-relevant features for few-shot learning by category traversal. In: CVPR, pp. 1–10 (2019)
Li, W., Jinglin, X., Huo, J., Wang, L., Gao, Y., Luo, J.: Distribution consistency based covariance metric networks for few-shot learning. Proc. AAAI Conf. Artif. Intell. 33, 8642–8649 (2019)
Lin, X., Sun, S., Huang, W., Sheng, B., Li, P., Feng, D.D.: EAPT: efficient attention pyramid transformer for image processing. IEEE Trans. Multimedia 25, 50–61 (2021)
Liu, Y., et al.: Learning to propagate labels: transductive propagation network for few-shot learning. arXiv preprint arXiv:1805.10002 (2018)
Mishra, N., Rohaninejad, M., Chen, X., Abbeel, P.: A simple neural attentive meta-learner. arXiv preprint arXiv:1707.03141 (2017)
Phaphuangwittayakul, A., Ying, F., Guo, Y., Zhou, L., Chakpitak, N.: Few-shot image generation based on contrastive meta-learning generative adversarial network. Vis. Comput. 39(9), 4015–4028 (2023)
Qi, G., Yu, H., Lu, Z., Li, S.: Transductive few-shot classification on the oblique manifold. In: ICCV, pp. 8412–8422 (2021)
Qian, K., Wen, X., Song, A.: Hybrid neural network model for large-scale heterogeneous classification tasks in few-shot learning. Vis. Comput. 38, 719–728 (2022)
Qin, Z., et al.: Multi-instance attention network for few-shot learning. Inf. Sci. 611, 464–475 (2022)
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211–252 (2015)
Simon, C., Koniusz, P., Nock, R., Harandi, M.: Adaptive subspaces for few-shot learning. In: CVPR, pp. 4136–4145 (2020)
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)
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., Wierstra, D., et al.: Matching networks for one shot learning. In: NIPS 2016: Proceedings of the 30th International Conference on Neural Information Processing Systems, vol. 29, pp. 3637–3645 (2016)
Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-UCSD birds-200-2011 dataset (2011)
Wu, Y., et al.: Object-aware long-short-range spatial alignment for few-shot fine-grained image classification. arXiv preprint arXiv:2108.13098 (2021)
Yang, F., Wang, R., Chen, X.: Sega: semantic guided attention on visual prototype for few-shot learning. In: WACV, pp. 1056–1066 (2022)
Zhang, C., Cai, Y., Lin, G., Shen, C.: DeepEMD: few-shot image classification with differentiable earth mover’s distance and structured classifiers. In: CVPR, pp. 12203–12213 (2020)
Zhao, K., Jin, X., Wang, Y.: Survey on few-shot learning. J. Softw. Eng. 32(2), 349–369 (2021)
Zhmoginov, A., Sandler, M., Vladymyrov, M.: HyperTransformer: model generation for supervised and semi-supervised few-shot learning. In: ICML, pages 27075–27098 (2022)
Zhou, Yu., Chen, Z., Sheng, B., Li, P., Kim, J., Enhua, W.: AFF-Dehazing: attention-based feature fusion network for low-light image dehazing. Comput. Animat. Virtual Worlds 32(3–4), e2011 (2021)
Zhu, H., Koniusz, P.: Ease: unsupervised discriminant subspace learning for transductive few-shot learning. In: CVPR, pp. 9078–9088 (2022)
Acknowledgments
Chen’s research was supported by the National Natural Science Foundation of China(Grant No.62202345).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Chen, J., Li, X., Ou, Y., Hu, X., Peng, T. (2024). MARANet: Multi-scale Adaptive Region Attention Network for Few-Shot Learning. In: Sheng, B., Bi, L., Kim, J., Magnenat-Thalmann, N., Thalmann, D. (eds) Advances in Computer Graphics. CGI 2023. Lecture Notes in Computer Science, vol 14495. Springer, Cham. https://doi.org/10.1007/978-3-031-50069-5_34
Download citation
DOI: https://doi.org/10.1007/978-3-031-50069-5_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-50068-8
Online ISBN: 978-3-031-50069-5
eBook Packages: Computer ScienceComputer Science (R0)