Abstract
In recent years, deep learning has become very popular and its application fields have been increasing, but it relies heavily on large number of labeled data. Therefore, it is necessary to find a few-shot learning method which can obtain a good training model using few samples. In this paper, a few-shot classification method based on MSFR is introduced for the ships classification task for the first time. In addition, we made a dataset of ships for the few-shot classification task, which we called FSCD. FSCD contains nine categories and 1500 samples. We used two methods of measuring learning called ProtoNet and MSFR, and a non-measuring method MAML for comparison. A large number of experiments have been implemented to prove that the performance of our proposed MSFR method on the ship dataset can reach 61% in 1-shot and 77.5% in 5-shot, which is better than the MAML and ProtoNet. In addition, we explore the effects of different network depths and different epochs on network performance in the ship dataset. As a few-shot ship classification study, this work opens up a new way of thinking and lays the foundation for further research.
Similar content being viewed by others
References
Zhou, X., Gong, W., Fu, W.L., et al.: Application of deep learning in object detection[C]. In: IEEE/ACIS 16th International Conference on Computer and Information Science (ICIS). IEEE, pp. 631–634. (2017)
Li, Y., Chao, X.: Semi-supervised few-shot learning approach for plant diseases recognition[J]. Plant Methods 17(1), 1–10 (2021)
Socher, R., Bengio, Y., Manning, C.D.: Deep learning for NLP (without magic) [M]. Tutorial Abstracts ACL 2012, 5–5 (2012)
Yang, J., Wen, J., Wang, Y., et al.: Fog-based marine environmental information monitoring toward ocean of things[J]. IEEE Internet Things J. 7(5), 4238–4247 (2019)
Li, Y., Chao, X.: ANN-based continual classification in agriculture[J]. Agriculture 10(5), 178 (2020)
Li, Y., Nie, J., Chao, X.: Do we really need deep CNN for plant diseases identification? [J]. Comput. Electron. Agric. 178, 105803 (2020)
Li, Y., Yang, J.: Few-shot cotton pest recognition and terminal realization[J]. Comput. Electron. Agric. 169, 105240 (2020)
Yang, J., Zhao, Y., Liu, J., et al.: No reference quality assessment for screen content images using stacked autoencoders in pictorial and textual regions[J]. IEEE Trans. Cybern. (2020). https://doi.org/10.1109/TCYB.2020.3024627
Yang, J., Xi, M., Jiang, B., et al.: FADN: fully connected attitude detection network based on industrial video[J]. IEEE Trans. Industr. Inf. 17(3), 2011–2020 (2020)
Guan, Q., Wang, Y., Ping, B., et al.: Deep convolutional neural network VGG-16 model for differential diagnosing of papillary thyroid carcinomas in cytological images: a pilot study[J]. J. Cancer 10(20), 4876 (2019)
Kaur, T., Gandhi, T.K.: Automated brain image classification based on VGG-16 and transfer learning[C]. In: International Conference on Information Technology (ICIT), IEEE, pp. 94–98. (2019).
Huang, G., Liu, Z., Van Der Maaten, L., et al.: Densely connected convolutional networks[C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4700–4708. (2017)
Szegedy, C., Liu, W., Jia, Y., et al.: Going deeper with convolutions[C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1–9. (2015)
He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition[C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770–778. (2016)
Ahmed, H., La, H.M., Tran, K.: Rebar detection and localization for bridge deck inspection and evaluation using deep residual networks[J]. Autom. Constr. 120, 103393 (2020)
Yang, J., Wen, J., Jiang, B., et al.: Blockchain-based sharing and tamper-proof framework of big data networking[J]. IEEE Network 34(4), 62–67 (2020)
Long, M., Wang, J., Ding, G., et al.: Transfer feature learning with joint distribution adaptation[C]. In: Proceedings of the IEEE international conference on computer vision, pp. 2200–2207. (2013)
Gong, B., Shi, Y., Sha, F., et al.: Geodesic flow kernel for unsupervised domain adaptation[C]. In: IEEE conference on computer vision and pattern recognition, IEEE, pp. 2066–2073. (2012)
Wang, Y., Yao, Q., Kwok, J.T., et al.: Generalizing from a few examples: a survey on few-shot learning[J]. ACM Comput. Surv. (CSUR) 53(3), 1–34 (2020)
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks[C]. In: International Conference on Machine Learning, PMLR, pp. 1126–1135. (2017)
Hariharan, B., Girshick, R.: Low-shot visual recognition by shrinking and hallucinating features[C]. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3018–3027. (2017)
Yang, Y., Zhang, Z., Mao, W., et al.: Radar target recognition based on few-shot learning[J]. Multimedia Syst. (2021). https://doi.org/10.1007/s00530-021-00832-3
Li, Y., Yang, J.: Meta-learning baselines and database for few-shot classification in agriculture[J]. Comput. Electron. Agric. 182, 106055 (2021)
Wang, Y.X., Girshick, R., Hebert, M., et al.: Low-shot learning from imaginary data[C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7278–7286. (2018)
Chao, X., Zhang, L.: Few-shot imbalanced classification based on data augmentation[J]. Multimedia Syst (2021). https://doi.org/10.1007/s00530-021-00827-0
Weinberger, K.Q., Saul, L.K.: Distance metric learning for large margin nearest neighbor classification[J]. J Mach Learn Res 10(2), 207–244 (2009)
Xue, T., Yu, H.: Model-agnostic metalearning-based text-driven visual navigation model for unfamiliar tasks[J]. IEEE Access 8, 166742–166752 (2020)
Deng, S., Zhang, N., Kang, J., et al.: Meta-learning with dynamic-memory-based prototypical network for few-shot event detection[C]. In: Proceedings of the 13th International Conference on Web Search and Data Mining, pp. 151-159. (2020)
Ketkar, N.: Stochastic Gradient Descent[M]. Deep Learning with Python, pp. 113–132. Apress, Berkeley (2017)
Lu, S., Lu, Z., Zhang, Y.D.: Pathological brain detection based on AlexNet and transfer learning[J]. J. Comput. Sci. 30, 41–47 (2019)
Liu, W., Wang, Z., Liu, X., et al.: A survey of deep neural network architectures and their applications[J]. Neurocomputing 234, 11–26 (2017)
Sung, F., Yang, Y., Zhang, L., et al.: Learning to compare: Relation network for few-shot learning[C]. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1199-1208. (2018)
Hui, B., Zhu, P., Hu, Q., et al.: Self-attention relation network for few-shot learning[C]. In: IEEE International Conference on Multimedia & Expo Workshops (ICMEW), IEEE, pp. 198-203. (2019)
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
About this article
Cite this article
Zhou, Y., Chen, C. & Ma, S. Few-shot ship classification based on metric learning. Multimedia Systems 29, 2877–2886 (2023). https://doi.org/10.1007/s00530-021-00847-w
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00530-021-00847-w