Abstract
Few-shot classification is a promising approach to solving the problem of classifying novel classes with only limited annotated data for training. Existing methods based on meta-learning predict novel-class labels for (target domain) testing tasks via meta knowledge learned from (source domain) training tasks of base classes. However, most existing works may fail to generalize to novel classes due to the probably large domain discrepancy across domains. To address this issue, we propose a novel adversarial feature augmentation (AFA) method to bridge the domain gap in few-shot learning. The feature augmentation is designed to simulate distribution variations by maximizing the domain discrepancy . During adversarial training, the domain discriminator is learned by distinguishing the augmented features (unseen domain) from the original ones (seen domain), while the domain discrepancy is minimized to obtain the optimal feature encoder. The proposed method is a plug-and-play module that can be easily integrated into existing few-shot learning methods based on meta-learning. Extensive experiments on nine datasets demonstrate the superiority of our method for cross-domain few-shot classification compared with the state of the art. Code is available at https://github.com/youthhoo/AFA_For_Few_shot_learning.
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
Similar content being viewed by others
References
Bateni, P., Barber, J., van de Meent, J., Wood, F.: Enhancing few-shot image classification with unlabelled examples. In: WACV (2022)
Bateni, P., Goyal, R., Masrani, V., Wood, F., Sigal, L.: Improved few-shot visual classification. In: CVPR (2020)
Bronskill, J., Gordon, J., Requeima, J., Nowozin, S., Turner, R.E.: Tasknorm: Rethinking batch normalization for meta-learning. In: ICML (2020)
Bronskill, J., Massiceti, D., Patacchiola, M., Hofmann, K., Nowozin, S., Turner, R.: Memory efficient meta-learning with large images. In: NeurIPS (2021)
Chen, W., Liu, Y., Kira, Z., Wang, Y.F., Huang, J.: A closer look at few-shot classification. In: ICLR (2019)
Deng, W., et al.: Deep ladder reconstruction-classification network for unsupervised domain adaptation. Pattern Recognit. Lett. 152, 398–405 (2021)
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., et al.: Model-agnostic meta-learning for fast adaptation of deep networks. In: ICML, vol. 70, pp. 1126–1135 (2017)
Fisher, R.A.: On the mathematical foundations of theoretical statistics. Philos. Trans. Royal Soc. London. Ser. A Cont. Papers Mathem. Phys. Charact. 222(594–604), 309–368 (1922)
Frikha, A., Krompaß, D., Köpken, H., Tresp, V.: Few-shot one-class classification via meta-learning. In: AAAI, pp. 7448–7456 (2021)
Ganin, Y., Lempitsky, V.S.: Unsupervised domain adaptation by backpropagation. In: Bach, F.R., Blei, D.M. (eds.) ICML, vol. 37, pp. 1180–1189 (2015)
Ganin, Y., et al.: Domain-adversarial training of neural networks. In: CVPR, pp. 189–209 (2017)
Ghifary, M., Kleijn, W.B., Zhang, M., Balduzzi, D., Li, W.: Deep reconstruction-classification networks for unsupervised domain adaptation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 597–613. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_36
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: ICLR (2015)
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
He, D., et al.: Stnet: Local and global spatial-temporal modeling for action recognition. In: AAAI, pp. 8401–8408 (2019)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
Horn, G.V., et al.: The inaturalist species classification and detection dataset. In: CVPR, pp. 8769–8778 (2018)
Hsu, H., et al.: Progressive domain adaptation for object detection. In: WACV, pp. 738–746. IEEE (2020)
Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3d object representations for fine-grained categorization. In: ICCV, pp. 554–561. IEEE Computer Society (2013)
Lake, B.M., Salakhutdinov, R., Tenenbaum, J.B.: Human-level concept learning through probabilistic program induction. Science 350(6266), 1332–1338 (2015)
Li, X., Wang, W., Hu, X., Yang, J.: Selective kernel networks. In: CVPR, pp. 510–519 (2019)
Li, Y., Yang, Y., Zhou, W., Hospedales, T.M.: Feature-critic networks for heterogeneous domain generalization. In: ICML, vol. 97, pp. 3915–3924 (2019)
Liu, B., et al.: Negative margin matters: understanding margin in few-shot classification. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 438–455. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58548-8_26
Liu, Y., et al.: Learning to propagate labels: Transductive propagation network for few-shot learning. In: ICLR (2019)
Long, M., Cao, Y., Wang, J., Jordan, M.I.: Learning transferable features with deep adaptation networks. In: ICML, pp. 97–105 (2015)
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. In: ICLR (2018)
Ravi, S., Larochelle, H.: Optimization as a model for few-shot learning. In: ICLR (2017)
Requeima, J., Gordon, J., Bronskill, J., Nowozin, S., Turner, R.E.: Fast and flexible multi-task classification using conditional neural adaptive processes. In: NeurIPS (2019)
Saito, K., Kim, D., Sclaroff, S., Darrell, T., Saenko, K.: Semi-supervised domain adaptation via minimax entropy. In: ICCV, pp. 8049–8057. IEEE (2019)
Satorras, V.G., Estrach, J.B.: Few-shot learning with graph neural networks. In: ICLR (2018)
Shafahi, A., et al.: Adversarial training for free! In: NeurIPS, pp. 3353–3364 (2019)
Sinha, A., Namkoong, H., Duchi, J.C.: Certifying some distributional robustness with principled adversarial training. In: ICLR (2018)
Snell, J., Swersky, K., Zemel, R.S.: Prototypical networks for few-shot learning. In: NeurIPS, pp. 4077–4087 (2017)
Splawa-Neyman, J., Dabrowska, D.M., Speed, T.: On the application of probability theory to agricultural experiments. essay on principles. section 9. Statistical Science, pp. 465–472 (1990)
Sui, D., Chen, Y., Mao, B., Qiu, D., Liu, K., Zhao, J.: Knowledge guided metric learning for few-shot text classification. In: NAACL-HLT, pp. 3266–3271. Association for Computational Linguistics (2021)
Sun, J., Lapuschkin, S., Samek, W., Zhao, Y., Cheung, N., Binder, A.: Explanation-guided training for cross-domain few-shot classification. In: ICPR, pp. 7609–7616 (2020)
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, pp. 1199–1208 (June 2018)
Tan, M., Le, Q.V.: Efficientnet: Rethinking model scaling for convolutional neural networks. In: ICML, vol. 97, pp. 6105–6114 (2019)
Tseng, H., Lee, H., Huang, J., Yang, M.: Cross-domain few-shot classification via learned feature-wise transformation. In: ICLR (2020)
Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: CVPR, pp. 2962–2971 (2017)
Vinyals, O., Blundell, C., Lillicrap, T., kavukcuoglu, k., Wierstra, D.: Matching networks for one shot learning. In: NeurIPS, pp. 3630–3638 (2016)
Volpi, R., Namkoong, H., Sener, O., Duchi, J.C., Murino, V., Savarese, S.: Generalizing to unseen domains via adversarial data augmentation. In: NeurIPS, pp. 5339–5349 (2018)
Wang, H., Deng, Z.: Cross-domain few-shot classification via adversarial task augmentation. In: Zhou, Z. (ed.) IJCAI, pp. 1075–1081 (2021)
Welinder, P., et al.: Caltech-ucsd birds 200 (2010)
Wu, F., Smith, J.S., Lu, W., Pang, C., Zhang, B.: Attentive prototype few-shot learning with capsule network-based embedding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12373, pp. 237–253. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58604-1_15
Wu, W., He, D., Lin, T., Li, F., Gan, C., Ding, E.: Mvfnet: Multi-view fusion network for efficient video recognition. In: AAAI, pp. 2943–2951 (2021)
Yeh, J., Lee, H., Tsai, B., Chen, Y., Huang, P., Hsu, W.H.: Large margin mechanism and pseudo query set on cross-domain few-shot learning. CoRR abs/2005.09218 (2020)
Yue, X., et al.: Prototypical cross-domain self-supervised learning for few-shot unsupervised domain adaptation. In: CVPR, pp. 13834–13844. IEEE (2021)
Zellinger, W., Grubinger, T., Lughofer, E., Natschläger, T., Saminger-Platz, S.: Central moment discrepancy (CMD) for domain-invariant representation learning. In: ICLR (2017)
Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., Torralba, A.: Places: A 10 million image database for scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. 40(6), 1452–1464 (2017)
Acknowledgments
This work was supported partially by NSFC (No. 61906218), Guangdong Basic and Applied Basic Research Foundation (No. 2020A1515011497), and Science and Technology Program of Guangzhou (No. 202002030371).
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
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Hu, Y., Ma, A.J. (2022). Adversarial Feature Augmentation for Cross-domain Few-Shot Classification. 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 13680. Springer, Cham. https://doi.org/10.1007/978-3-031-20044-1_2
Download citation
DOI: https://doi.org/10.1007/978-3-031-20044-1_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20043-4
Online ISBN: 978-3-031-20044-1
eBook Packages: Computer ScienceComputer Science (R0)