Abstract
Few-shot learning aims to use limited labeled samples to achieve effective classification results. To mine the features of images in a limited number of pieces, some researchers proposed to drill salient features to improve the classification effect. However, they ignore the use of salient secondary features. Therefore, we offer to use salient secondary features to supplement the deficiency of salient features. Combining with the foreground extraction network and the graph neural network, a better classification effect is obtained in the experiment.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Fe-Fei L (2003) A Bayesian approach to unsupervised one-shot learning of object categories. In: Proceedings of ninth IEEE international conference on computer vision. IEEE, pp 1134–1141
Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. In: Advances in neural information processing systems, pp 4077–4087
Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In: Proceedings of international conference on machine learning, pp 1126–1135.
Satorras VG, Estrach JB (2018) Few-shot learning with graph neural networks
Kim J, Kim T, Kim S, Yoo D (2019) Edge-labeling graph neural network for few-shot learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 11–20
Gidaris S, Komodakis N (2019) Generating classification weights with GNN denoising autoencoders for few-shot learning. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 21–30
Zhang X, Zhang Y, Zhang Z, Liu J (2022) Discriminative learning of imaginary data for few-shot classification. Neurocomputing 467:406–417
Qin X, Zhang Z, Huang C, Chao G, Dehghan M, Jagersand M (2019) BASNet: boundary-aware salient object detection. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 7479–7489
Zhang J, Zhang M, Lu Z, Tao X (2021) AdarGCN: adaptive aggregation GCN for few-shot learning. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision. IEEE Press, Nashville, pp 3482–3491
Zhang M, Zhang J, Lu Z, Tao X, Ding M, Huang S (2021) IEPT: instance-level and episode-level pretext tasks for few-shot learning. In: International conference on learning representations
An Y, Xue H, Zhao X, Zhang L (2021) Conditional self-supervised learning for few-shot classification. IJCAI 2140–2146
Acknowledgements
This research is sponsored by Natural Science Foundation of Chongqing (cstc2018jscx-mszdX0116), China.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liu, C., Hou, W., Wang, X., Zhang, X. (2023). Secondary Salient Feature-Based GNN for Few-Shot Classification. In: Park, J.S., Yang, L.T., Pan, Y., Park, J.H. (eds) Advances in Computer Science and Ubiquitous Computing. CUTECSA 2022. Lecture Notes in Electrical Engineering, vol 1028. Springer, Singapore. https://doi.org/10.1007/978-981-99-1252-0_7
Download citation
DOI: https://doi.org/10.1007/978-981-99-1252-0_7
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-1251-3
Online ISBN: 978-981-99-1252-0
eBook Packages: EngineeringEngineering (R0)