Abstract
This paper presents an innovative method for self-supervised learning in image classification, leveraging the contrastive learning paradigm. The proposed framework incorporates the SEResNet50 backbone and employs the contrastive loss function to facilitate the learning of discriminative features. Additionally, a local self-attention mechanism is introduced in the classification head following transfer learning. This work contributes in two main aspects: firstly, the proposed framework demonstrates an approximate 3% improvement in classification accuracy compared to the baseline approach; secondly, it significantly reduces training time and enhances convergence rate. Experimental evaluations on the STL-10 dataset validate the superior performance of the proposed framework over the baseline approach. Moreover, the local self-attention mechanism proves to be effective in enhancing the discriminative power of the learned features. In conclusion, this paper introduces a novel framework for self-supervised learning, which combines the SEResNet50 backbone, contrastive loss function, and local self-attention mechanism. The proposed approach achieves exceptional performance and reduces training time, thus exhibiting great promise for image classification tasks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hjelm, R.D., et al.: Learning deep representations by mutual information estimation and maximization. arXiv preprint arXiv:1808.06670 (2018)
Bachman, P., Hjelm, R.D., Buchwalter, W.: Learning representations by maximizing mutual information across views. In: NIPS, pp. 15509–15519 (2019)
Tian, Y., Krishnan, D., Isola, P.: Contrastive multiview coding. arXiv preprint arXiv:1906.05849 (2019)
Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: CVPR, pp. 3733–3742 (2018)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. arXiv preprint arXiv:2002.05709 (2020)
He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. arXiv preprint arXiv:1911.05722 (2019)
Grill, J.-B., et al.: Bootstrap your own latent: a new approach to self-supervised learning. arXiv preprint arXiv:2006.07733 (2020)
Chen, X., He, K.: Exploring simple Siamese representation learning. arXiv preprint arXiv:2011.10566 (2020)
Li, J., Zhou, P., Xiong, C., Socher, R., Hoi, S.C.: Prototypical contrastive learning of unsupervised representations. arXiv preprint arXiv:2005.04966 (2020)
Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. arXiv preprint arXiv:2006.09882 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Cao, J., Chi, D., Han, J. (2024). Image Classification Method Base on Contrastive Learning. In: Li, J., Zhang, B., Ying, Y. (eds) 6GN for Future Wireless Networks. 6GN 2023. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 554. Springer, Cham. https://doi.org/10.1007/978-3-031-53404-1_19
Download citation
DOI: https://doi.org/10.1007/978-3-031-53404-1_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-53403-4
Online ISBN: 978-3-031-53404-1
eBook Packages: Computer ScienceComputer Science (R0)