Abstract
The few-shot learning method based on local feature attention can suppress the irrelevant distraction in the global information and extract discriminating features. However, empirically defining the relationship between local features cannot fully utilize the power of local feature attention. This paper proposes a local feature graph neural network model (LFGNN), which uses the GNN to automatically extract and aggregate the relationship between different local parts and obtain features with stronger expressive ability for classification. Specifically, a sparse hierarchical connectivity graph is proposed to describe the relationship between features, in which the global features of all samples in the support set and the query set are connected in pairs, and the local features of each sample are only connected to the corresponding global features. Further, a multiple node-edge aggregation strategy is developed to learn a similarity metric. By integrating the edge loss with the classification loss, our LFGNN learns a better classifier to distinguish samples of novel classes. We conducted extensive experiments under the 5-way 1-shot and 5-way 5-shot setting on two benchmark datasets: miniImageNet, tieredImageNet. Experimental results demonstrate that the proposed approach is effective for boosting performance of meta-learning few-shot classification.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Cao K, Ji J, Cao Z, Chang C-Y, Niebles JC (2019) Few-shot video classification via temporal alignment
Chang X, Nie F, Wang S, Yang Y, Zhou X, Zhang C (2016) Compound rank-\(k\) projections for bilinear analysis. IEEE Trans Neural Netw Learn Syst 27(7):1502–1513. https://doi.org/10.1109/TNNLS.2015.2441735
Chen K, Yao L, Zhang D, Wang X, Chang X, Nie F (2020) A semisupervised recurrent convolutional attention model for human activity recognition. IEEE Trans Neural Netw Learn Syst 31(5):1747–1756. https://doi.org/10.1109/TNNLS.2019.2927224
Chen WY, Liu YC, Kira Z, Wang YCF, Huang JB (2019) A closer look at few-shot classification, In arXiv
Chen Y, Wang X, Liu Z, Xu H, Darrell T (2020b) A new meta-baseline for few-shot learning. arXiv preprint arXiv:2003.04390
Fe-Fei L et al (2003) A bayesian approach to unsupervised one-shot learning of object categories. In Proceedings Ninth IEEE International Conference on Computer Vision, pages 1134–1141 IEEE
Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In International Conference on Machine Learning, pages 1126–1135. PMLR
Garcia V, Bruna J (2017) Few-shot learning with graph neural networks. arXiv preprint arXiv:1711.04043
Graves A, Wayne G, Danihelka I (2014) Neural turing machines. arXiv preprint arXiv:1410.5401
Herbelot A, Baroni M (2017) High-risk learning: acquiring new word vectors from tiny data. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 304–309, Copenhagen, Denmark. Association for Computational Linguistics. https://doi.org/10.18653/v1/D17-1030
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
Hou R, Chang H, Ma B, Shan S, Chen X (2019) Cross attention network for few-shot classification. arXiv preprint arXiv:1910.07677
Jie S, Samuel A, Gang SE (2019) Squeeze-and-excitation networks. IEEE Trans Pattern Anal Mach Intell
Kim J, Kim T, Kim S, Yoo CD (2019) Edge-labeling graph neural network for few-shot learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11–20
Koch G, Zemel R, Salakhutdinov R (2015) Siamese neural networks for one-shot image recognition. In ICML deep learning workshop, volume 2. Lille
Lee K, Maji S, Ravichandran A, Soatto S (2019) Meta-learning with differentiable convex optimization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10657–10665
Li A, Huang W, Jiashi F, Lan X, Li Z, Wang L (2020) Boosting few-shot learning with adaptive margin loss. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12576–12584
Li Z, Nie F, Chang X, Nie L, Zhang H, Yang Y (2018) Rank-constrained spectral clustering with flexible embedding. IEEE Trans Neural Netw Learn Syst 29(12):6073–6082. https://doi.org/10.1109/TNNLS.2018.2817538
Li Z, Nie F, Chang X, Yang Y, Zhang C, Sebe N (2018) Dynamic affinity graph construction for spectral clustering using multiple features. IEEE Trans Neural Netw Learn Syst 29(12):6323–6332. https://doi.org/10.1109/TNNLS.2018.2829867
Lin G, Yang Y, Fan Y, Kang X, Liao K, Zhao F (2020) High-order structure preserving graph neural network for few-shot learning
Liu M-Y, Huang X, Mallya A, Karras T, Aila T, Lehtinen J, Kautz J (2019) Few-shot unsupervised image-to-image translation. ICCV 2019
Liu Y, Lee J, Park M, Kim S, Yang E, Hwang SJ, Yang Y (2018) Learning to propagate labels: Transductive propagation network for few-shot learning. arXiv preprint arXiv:1805.10002
Luo M, Chang X, Nie L, Yang Y, Hauptmann AG, Zheng Q (2018) An adaptive semisupervised feature analysis for video semantic recognition. IEEE Trans Cybern 48(2):648–660. https://doi.org/10.1109/TCYB.2017.2647904
Munkhdalai T, Yu H (2017) Meta networks. In International Conference on Machine Learning, pages 2554–2563. PMLR
Nichol A, Achiam J, Schulman J (2018) On first-order meta-learning algorithms. arXiv preprint arXiv:1803.02999
Park J, Woo S, Lee JY, Kweon IS (2018) Bam: Bottleneck attention module. In Computer Vision and Pattern Recognition
Pham TX, Mina Rjl, Issa D, Yoo CD (2021) Self-supervised learning with local attention-aware feature. In Computer Vision and Pattern Recognition
Ren L, Duan G, Huang T, Kang Z (2022) Multi-local feature relation network for few-shot learning. Neural Comput Appl 34(10):7393–7403
Ren M, Triantafillou E, Ravi S, Snell J, Swersky K, Tenenbaum JB, Larochelle H, Zemel RS (2018) Meta-learning for semi-supervised few-shot classification. arXiv preprint arXiv:1803.00676
Rubner Y, Tomasi C, Guibas LJ (2000) The earth mover’s distance as a metric for image retrieval. Int J Comput Vision 40(2):99–121
Santoro A, Bartunov S, Botvinick M, Wierstra D, Lillicrap T (2016) One-shot learning with memory-augmented neural networks. arXiv preprint arXiv:1605.06065
Scarselli F, Gori M, Tsoi AC, Hagenbuchner M, Monfardini G (2009) The graph neural network model. IEEE Trans Neural Networks 20(1):61
Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. Adv Neural Inf Process Syst 30:4077–4087
Snell J, Swersky K, Zemel RS (2017b) Prototypical networks for few-shot learning. arXiv preprint arXiv:1703.05175
Song Y, Liu Z, Bi W, Yan R, Zhang M (2019) Learning to customize model structures for few-shot dialogue generation tasks
Sung F, Yang Y, Zhang L, Xiang T, Torr PHS, Hospedales TM (2018) Learning to compare: relation network for few-shot learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 1199–1208
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In arXiv
Vinyals O, Blundell C, Lillicrap T, Kavukcuoglu K, Wierstra D (2016a) Matching networks for one shot learning. arXiv preprint arXiv:1606.04080
Vinyals O, Blundell C, Lillicrap T, Kavukcuoglu K, Wierstra D (2016) Matching networks for one shot learning. Adv Neural Inf Process Syst 29:3630–3638
Wang T-C, Liu M-Y Andrew T, Jan K, Bryan C (2019) Few-shot video-to-video synthesis
Xiang L, Jin X, Ding G, Han J, Li L (2019) Incremental few-shot learning for pedestrian attribute recognition
Shiyao X, Yang X (2021) Frog-gnn: Multi-perspective aggregation based graph neural network for few-shot text classification. Exp Syst App 176:114795. https://doi.org/10.1016/j.eswa.2021.114795
Yan C, Chang X, Luo M, Zheng Q, Zhang X, Li Z, Nie F (2020) Self-weighted robust lda for multiclass classification with edge classes. ACM Trans Intell Syst Technol. https://doi.org/10.1145/3418284
Yang L, Li L, Zhang Z, Zhou X, Zhou E, Yu L (2020) Distribution propagation graph network for few-shot learning, Dpgn
En Y, Ma J, Sun J, Chang X, Zhang H, Hauptmann Alexander G (2022) Deep discrete cross-modal hashing with multiple supervision. Neurocomputing 486:215–224. ISSN 0925-2312. https://doi.org/10.1016/j.neucom.2021.11.035
Zhang J, Zhang M, Zhiwu L, Xiang T, Jirong W (2020) Adaptive aggregation gcn for few-shot learning, Adargcn
Zhou R, Chang X, Shi L, Shen Y-D, Yang Y, Nie F (2020) Person reidentification via multi-feature fusion with adaptive graph learning. IEEE Trans Neural Netw Learn Syst 31(5):1592–1601. https://doi.org/10.1109/TNNLS.2019.2920905
Author information
Authors and Affiliations
Corresponding author
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
Weng, P., Dong, S., Ren, L. et al. Local feature graph neural network for few-shot learning. J Ambient Intell Human Comput 14, 4343–4354 (2023). https://doi.org/10.1007/s12652-023-04545-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-023-04545-5