Abstract
Cross-Domain Few-Shot Learning (CDFSL) is one of the most cutting-edge fields in machine learning. It not only addresses the traditional few-shot problem but also allows for different distributions between base classes and novel classes. However, most current CDFSL models only focus on the generalization performance of high-level features during training and testing, which hinders their ability to generalize well to domains with significant gaps. To overcome this problem, we propose a CDFSL method based on Task Augmentation and Multi-Level Adaptive features representation(TA-MLA). At the feature representation level, we introduce a meta-learning strategy for multi-level features and adaptive features. The former come from different layers of network. They jointly participate in image prediction to fully explore transferable features suitable for cross-domain scenarios. The latter is based on a feature adaptation module of feed-forward attention, aiming to learn domain-adaptive features to improve the generalization of the model. At the training task level, we employ a plug-and-play Task Augmentation(TA) module to generate challenging tasks with adaptive inductive biases, thereby expanding the distribution of the source domain and further bridging domain gaps. Extensive experiments conducted on multiple datasets. The results demonstrate that our method based on meta-learning can effectively improves few-shot classification performance, especially in cases with significant domain shift.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10489-024-06110-9/MediaObjects/10489_2024_6110_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10489-024-06110-9/MediaObjects/10489_2024_6110_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10489-024-06110-9/MediaObjects/10489_2024_6110_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10489-024-06110-9/MediaObjects/10489_2024_6110_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10489-024-06110-9/MediaObjects/10489_2024_6110_Figa_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10489-024-06110-9/MediaObjects/10489_2024_6110_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10489-024-06110-9/MediaObjects/10489_2024_6110_Fig6_HTML.png)
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Data Availability
The five datasets used and analysed during the current study are available at https://image-net.org/, https://www.kaggle.com/saroz014/plant-disease/, http://madm.dfki.de/downloads, http://challenge2018.isic-archive.com, https://www.kaggle.com/nih-chest-xrays/data, http://www.vision.caltech.edu/visipedia-data/CUB-200-2011/CUB_200_2011.tgz and http://imagenet.stanford.edu/internal/car196/cars_train.tgz
References
Gong X, Yao Z, Li X (2022) LAG-Net: multi-granularity network for person re-identification via local attention system. IEEE Trans Multimed 24(1):217–229. https://doi.org/10.1109/TMM.2021.3050082
Zhai D, Hu B, Gong X, Zou H, Luo J (2022) ASS-GAN: asymmetric semi-supervised GAN for Breast Ultrasound Image Segmentation. Neurocomputing 493(7):204–216
Gong X, Tan X, Xiang Y (2024) Contrastive Mean teacher for intra-camera supervised person re-identification. IEEE Transactions on Circuits and Systems for Video Technology. https://doi.org/10.1109/TCSVT.2024.3402533
Wang Y, Yao Q, Kwok JT, Ni LM (2020) Generalizing from a few examples: A survey on few-shot learning. ACM Comput Surv (csur) 53(3):1–134
Rizve MN, Khan S, Khan FS, Shah M (2021) 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 10836–10846
Luo X, Wei L, Wen L, Yang J, Xie L, Xu Z, Tian Q (2021) Rectifying the shortcut learning of background for few-shot learning. Adv Neural Inf Process Syst 34:13073–13085
Guo Y, Codella NC, Karlinsky L, Codella JV, Smith JR, Saenko K, Rosing T, Feris R (2020) A broader study of cross-domain few-shot learning. In: Computer Vision–ECCV 2020: 16th European Conference, vol. 42, pp 124–141. Springer, Heidelberg
Wang H, Deng Z-H (2021) Cross-domain few-shot classification via adversarial task augmentation. In: Proceedings of the thirtieth international joint conference on artificial intelligence, IJCAI 1075–1081
Tseng H-Y, Lee H-Y, Huang J-B, Yang M-H (2020) Cross-domain few-shot classification via learned feature-wise transformation. In: 8th International Conference on Learning Representations, ICLR
Hu Y, Ma AJ (2022) Adversarial feature augmentation for cross-domain few-shot classification. In: European conference on computer vision, ECCV, 20–37
Fu Y, Xie Y, Fu Y, Chen J, Jiang Y-G (2022) Wave-san: Wavelet based style augmentation network for cross-domain few-shot learning. Preprint at arXiv:2203.07656
Zhou F, Wang P, Zhang L, Wei W, Zhang Y (2023) Revisiting prototypical network for cross domain few-shot learning. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition 20061–20070
Zhang J, Song J, Gao L, Shen H (2022) Free-lunch for cross-domain few-shot learning: Style-aware episodic training with robust contrastive learning. In: Proceedings of the 30th ACM international conference on multimedia 2586–2594
Fu Y, Xie Y, Fu Y, Jiang Y-G (2023) Styleadv: Meta style adversarial training for cross-domain few-shot learning. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition 24575–24584
Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition 7132–7141
Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In: International conference on machine learning 1126–1135
Nichol A, Schulman J (2018) Reptile: a scalable metalearning algorithm. 2(3):4. arXiv:1803.02999
Baik S, Hong S, Lee KM (2020) Learning to forget for meta-learning. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition 2379–2387
Baik S, Choi M, Choi J, Kim H, Lee KM (2020) Meta-learning with adaptive hyperparameters. Adv Neural Inf Process Syst 22:20755–20765
Baik S, Choi J, Kim H, Cho D, Min J, Lee KM (2021) Meta-learning with task-adaptive loss function for few-shot learning. In: Proceedings of the IEEE/CVF international conference on computer vision 9465–9474
BVinyals O, Blundell C, Lillicrap T, Wierstra D, et al (2016) Matching networks for one shot learning. Adv Neural Info Process Syst 29
Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. Adv Neural Inf Process Syst 30
Garcia V, Bruna J (2018) Few-shot learning with graph neural networks. In: 6th International conference on learning representations, ICLR
Huang H, Wu Z, Li W, Huo J, Gao Y (2021) Local descriptor-based multi-prototype network for few-shot learning. Pattern Recognition 116:107935
Chen W-Y, Liu Y-C, Kira Z, Wang Y-CF, Huang J-B (2019) A closer look at few-shot classification. In: 7th international conference on learning representations, ICLR
Sun Q, Liu Y, Chua T-S, Schiele B (2019) Meta-transfer learning for few-shot learning. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition 403–412
Wertheimer D, Tang L, Hariharan B (2021) Few-shot classification with feature map reconstruction networks. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition 8012–8021
Wang R, Wu Z, Weng Z, Chen J, Qi G-J, Jiang Y-G (2022) Cross-domain contrastive learning for unsupervised domain adaptation. IEEE Trans Multimed 25:1665–1673
Tang H, Jia K (2020) Discriminative adversarial domain adaptation. In: Proceedings of the AAAI conference on artificial intelligence 5940–5947
Alanov A, Titov V, Vetrov DP (2022) Hyperdomainnet: Universal domain adaptation for generative adversarial networks. Adv Neural Inf Process Syst 35:29414–29426
Wang J, Lan C, Liu C, Ouyang Y, Qin T, Lu W, Chen Y, Zeng W, Philip SY (2022) Generalizing to unseen domains: A survey on domain generalization. IEEE Trans Knowl Data Eng 35(8):8052–8072
Li P, Liu F, Jiao L, Li S, Li L, Liu X, Huang X (2023) Knowledge transduction for cross-domain few-shot learning. Pattern Recognition 141:109652
Li W-H, Liu X, Bilen H (2021) Universal representation learning from multiple domains for few-shot classification. In: Proceedings of the IEEE/CVF international conference on computer vision 9526–9535
Dvornik N, Schmid C, Mairal J (2020) Selecting relevant features from a multi-domain representation for few-shot classifica-tion. In: European conference on computer vision, ECCV 769–786
Xu H, Zhi S, Liu L (2023) Cross-domain few-shot classification via inter-source stylization. In: IEEE International conference on image processing (ICIP) 565–569
Phoo CP, Hariharan B (2021) Self-training for few-shot transfer across extreme task differences. In: 9th International conference on learning representations, ICLR
Islam A, Chen C-FR, Panda R, Karlinsky L, Feris R, Radke RJ (2021) Dynamic distillation network for cross-domain few-shot recognition with unlabeled data. Adv Neural Inf Process Syst 34:3584–3595
Fu Y, Xie Y, Fu Y, Chen J, Jiang Y-G (2022) Me-d2n: Multi-expert domain decompositional network for cross-domain few-shot learning. In: Proceedings of the 30th ACM international conference on multimedia 6609–6617
Fu Y, Fu Y, Jiang Y-G (2021) Meta-fdmixup: Cross-domain few-shot learning guided by labeled target data. In: Proceedings of the 29th ACM international conference on multimedia 5326–5334
Yosinski J, Clune J, Bengio Y, Lipson H (2014) How transferable are features in deep neural networks? Adv Neural Inf Process Syst 27
Long M, Cao Y, Wang J, Jordan M (2015) Learning transferable features with deep adaptation networks. In: International conference on machine learning, PMLR 97–105
Zhang X-Y, Huang Y-P, Mi Y, Pei Y-T, Zou Q, Wang S (2021) Video sketch: A middle-level representation for action recognition. Appl Intell 51:2589–2608
Lei J, Liu Z, Zou Z, Li T, Xu J, Wang S, Yang G, Feng Z (2022) Facial Expression Recognition with Mid-level Representation Enhancement and Graph Embedded Uncertainty Suppressing. In: European conference on computer vision, ECCV 93–103
Liang M, Huang S, Pan S, Gong M, Liu W (2022) Learning multi-level weight-centric features for few-shot learning. Pattern Recognition 128:108662
Maaten L, Hinton G (2008) Visualizing data using t-sne. J Mach Learn Res 9
Acknowledgements
The authors thank the anonymous referees for their valuable comments. This paper is in part supported by the National Natural Science Foundation of China under Grants 62376231, the Sichuan Science and Technology Program 2023YFS0202 and 2023YFG0267, respectively.
Author information
Authors and Affiliations
Contributions
Ling Yue and Lin Feng drafted the manuscript. Ling Yue completed the code. Qiuping Shuai, Zihao Li and Lingxiao Xu designed experiments. All authors have read and agreed to the published version of the manuscript.
Corresponding author
Ethics declarations
Competing Interests
All the authors declare that they have no competing financial interests or personal relationships that could influence the work reported in this paper.
Ethics approval
Not applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Yue, L., Feng, L., Shuai, Q. et al. Multi-level adaptive feature representation based on task augmentation for Cross-Domain Few-Shot learning. Appl Intell 55, 291 (2025). https://doi.org/10.1007/s10489-024-06110-9
Accepted:
Published:
DOI: https://doi.org/10.1007/s10489-024-06110-9