Abstract
Classical machine learning works ineffectively when the data set is small. Recently, few-shot learning is proposed to solve this problem. Few-shot learning models a few samples through the prior knowledge. We could divide few-shot learning into various categories depending on where the prior knowledge is extracted from. There are mainly three classes in this paper: (i) the prior knowledge extracted from the labeled data; (ii) the prior knowledge extracted from a weakly labeled or unlabeled data set; (iii) the prior knowledge extracted from similar data sets. For the convenience of searching corresponding few-shot learning methods in a certain domain, based on the above classification, we further classify few-shot learning models into ones which are applied to the image domain and the other which are applied to the text domain. With this taxonomy, we review the previous works on few-shot learning and discuss them according to these categories. Finally, present challenges and promising directions, in the aspect of few-shot learning, are also proposed.
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
Wang, J., Zhang, T., Cheng, Y., Al-Nabhan, N.: Deep learning for object detection: a survey. Comput. Syst. Sci. Eng. 38(2), 165–182 (2021)
Deng, C., Zeng, G., Cai, Z., Xiao, X.: A survey of kowledge based question answering with deep learning. J. Artif. Intel. 2(4), 157–166 (2020)
Liu, X., Chen, X.: A survey of gan-generated fake faces detection method based on deep learning. J. Info. Hid. Priva. Protec. 2(2), 87–94 (2020)
Jankowski, N., Duch, W., Grąbczewski, K.: Meta-learning in computational intelligence. Springer Science and Business Media. 97−115 (2011)
Lake, B., Salakhutdinov, R.: One-shot learning by inverting a compositional causal process. In: Advances in Neural Information Processing Systems, pp. 2526−2534 (2013)
Yang, J., Liu, Y.L.: The latest advances in face recognition with single training sample. J. Xihua Univ. (Natural Science Edition) 33(4), 1−5 (2014). (in Chinese)
Gamal, M., Abbas, H.M., Moustafa, N., Sitnikova, E., Sadek, R.A.: Few-shot learning for discovering anomalous behaviors in edge networks. Computers, Materials & Continua 69(2), 1823–1837 (2021)
Zhang, B., Ling, H., Li, P.: Multi-head attention graph network for few shot learning. Computers, Materials & Continua 68(2), 1505–1517 (2021)
Wang, Y., Yao, Q., Kwok, J.: Generalizing from a few examples: a survey on few-shot. Learning 53(3), 1–34 (2020)
Miller, E., Matsakis, N., Viola P.: Learning from one example through shared densities on transforms. In: CVPR 2000, pp. 464–471. IEEE (2000)
Hariharan, B., Girshick, R.: Low-shot visual recognition by shrinking and hallucinating features. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3018–3027 (2017)
Schwartz, E., et al.: Delta-encoder: an effective sample synthesis method for few-shot object recognition. arXiv:1806.04734 (2018)
Jason, W., Zou, K.: EDA: Easy data augmentation techniques for boosting performance on text classification tasks. arXiv:1901.11196 (2019)
Anaby-Tavor, A., et al.: Do not have enough data? deep learning to the rescue! arXiv: 1911.03118v2 (2019)
Keshari, R., et al.: Learning structure and strength of CNN filters for small sample size training. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9349–9358 (2018)
Pfister, T., Charles, J., Zisserman, A.: Domain-adaptive discriminative one-shot learning of gestures. In: European Conference on Computer Vision, pp. 814–829 (2014)
Douze, M., et al.: Low-shot learning with large-scale diffusion. In: Conference on Computer Vision and Pattern Recognition, pp. 3349–3358 (2018)
Xie, Q., et al.: Unsupervised Data Augmentation for Consistency Training. arXiv:1904.12848 (2019)
Bailey, K., Chopra, S.: Few-shot text classification with pre-trained word embeddings and a human in the loop. arXiv: 1804.02063 (2018)
Tsai, Y., Salakhutdinov, R.: Improving one-shot learning through fusing side information. arXiv:1710.08347 (2017)
Gao, H., et al.: Low-shot learning via covariance-preserving adversarial augmentation networks. In: Advances in Neural Information Processing Systems, pp. 983–993 (2018)
Chen, W., et al.: Few-shot learning with part discovery and augmentation from unlabeled images. arXiv:2105.11874 (2021)
Xu, X., et al.: AUGNLG: few-shot natural language generation using self-trained data augmentation. arXiv: 2106.05589 (2021)
Motiian, S., et al.: Few-shot adversarial domain adaptation. In: Advances in Neural Information Processing Systems, pp. 6670–6680 (2017)
Luo, Z., et al.: Label efficient learning of transferable representations across domains and tasks. In: Advances in Neural Information Processing Systems, pp. 165–177 (2017)
Zhang, Y., Tang, H., Jia, K.: Fine-grained visual categorization using meta-learning optimization with sample selection of auxiliary data. In: European Conference on Computer Vision, pp. 233–248 (2018)
Hu, Z., et al.: Few-shot charge prediction with discriminative legal attributes. In: International Conference on Computational Linguistics, pp. 487–498 (2018)
Yu, M., et al.: Diverse few-shot text classification with multiple metrics. arXiv: 1805.07513 (2018)
Han, C., et al.: Meta-learning adversarial domain adaptation network for few-shot text classification. arXiv: 2107.12262 (2021)
Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: Advances in Neural Information Processing Systems, pp. 4077–4087 (2017)
Bateni, P., et al.: Improved few-shot visual classification. arXiv: 1912.03432 (2020)
Vinyals, O., et al.: Matching networks for one shot learning. In: Advances in Neural Information Processing Systems, pp. 3630–3638 (2016)
Requeima, J., et al.: Fast and flexible multi-task classification using conditional neural adaptive processes. arXiv:1906.07697 (2019)
Bertinetto, L., et al.: Learning feed-forward one-shot learners. In: Advances in Neural Information Processing Systems, pp. 523–531 (2016)
Oreshkin, B., López, P. R., and Lacoste, A.: TADAM: Task dependent adaptive metric for improved few-shot learning. In: Advances in Neural Information Processing Systems, pp. 719–729 (2018)
Zhao, F., et al.: Dynamic conditional networks for few-shot learning. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 19–35 (2018)
Pan, C., Huang, J., Gong, J., Yuan, X.: Few-shot transfer learning for text classification with lightweight word embedding based models. IEEE Access 7, 53296–53304 (2019)
Hu, M., et al.: Multi-label few-shot learning for aspect category detection. arXiv:2105.14174 (2021)
Yoo, D., Fan, H., Boddeti, V.N., Kitani, K.M.: Efficient k-shot learning with regularized deep networks. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)
Shen, Z., et al.: Partial is better than all: revisiting fine-tuning strategy for few-shot learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 11, pp. 9594–9602 (2021)
Rizve, M.N., et al.: Exploring complementary strengths of invariant and equivariant representations for few-shot learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10836–10846 (2021)
Howard, J., Ruder, S.: Universal language model fine-tuning for text classification. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (2018)
Peng, B., et al.: Few-shot natural language generation for task-oriented dialog. arXiv:2002.1232 (2020)
Fort, S.: Gaussian prototypical networks for few-shot learning on Omniglot. arXiv:1708.02735 (2017)
Malalur, P., Jaakkola, T.: Alignment based matching networks for one-shot classification and open-set recognition. arXiv:1903.06538 (2019)
Cui, Y., et al.: Fine-grained categorization and dataset bootstrapping using deep metric learning with humans in the loop. In: Proc. of the IEEE conference on computer vision and pattern recognition, pp. 1153−1162 (2016)
Novikova, J., Dusek, O., Rieser, V.: The e2e dataset: New challenges for end-to-end generation. arXiv:1706.09254 (2017)
Wen, T. H., et al.: Multidomain neural network language generation for spoken dialogue systems. arXiv:1603.01232 (2016)
Mairesse, F., et al.: Phrase-based statistical language generation using graphical models and active learning. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pp. 1552–1561 (2010)
Krizhevsky, A., Nair, V., Hinton, G.: Cifar-100 (canadian institute for advanced research) (2009)
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
Zhang, Z., Liu, Y., Huang, J. (2022). Review of Few-Shot Learning in the Text Domain and the Image Domain. In: Sun, X., Zhang, X., Xia, Z., Bertino, E. (eds) Advances in Artificial Intelligence and Security. ICAIS 2022. Communications in Computer and Information Science, vol 1587. Springer, Cham. https://doi.org/10.1007/978-3-031-06761-7_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-06761-7_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-06760-0
Online ISBN: 978-3-031-06761-7
eBook Packages: Computer ScienceComputer Science (R0)