Image classification framework based on contrastive self-supervised learning

被引：0
|
作者：
Zhao H.-W. [1 ]
Zhang J.-R. [1 ]
Zhu J.-P. [2 ]
Li H. [1 ]
机构：
[1] College of Computer Science and Technology, Jilin University, Changchun
[2] Shanghai Zhengen Industrial Co., Ltd., Shanghai
来源：
Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition) | 2022年 / 52卷 / 08期
关键词：
computer application; contrastive learning; image classification; self-supervised learning;
D O I：
10.13229/j.cnki.jdxbgxb20210607
中图分类号：
学科分类号：
摘要：
In order to solve the problem that supervised learning needs a lot of time to complete data set annotation in the field of image classification, a self-supervised image classification framework, SSIC framework, is proposed. SSIC framework is a self supervised learning method based on contrastive learning, which has better performance than the existing unsupervised methods. A new framework is designed and a more effective pretext task is selected to improve the robustness of the model. In addition, a targeted loss function is proposed to improve the performance of image classification. experiments was conducted on UC Merced, NWPU and AID data sets. Experimental results show that SSIC framework has obvious advantages over the latest technology, and it also performs well in low resolution image classification. © 2022 Editorial Board of Jilin University. All rights reserved.
引用
收藏
页码：1850 / 1856
页数：6
相关论文
共 17 条
  • [1] Lowe D G., Distinctive image features from scale-invariant key points, International Journal of Computer Vision, 60, 2, pp. 91-110, (2004)
  • [2] Zhao Hong-wei, Huo Dong-sheng, Wang Jie, Et al., Image classification of insect pests based on saliency detection, Journal of Jilin University(Engineering and Technology Edition), 51, 6, pp. 2174-2181, (2021)
  • [3] Xu Qian-yi, Qin Gui-he, Sun Ming-hui, Et al., Classification of drivers' head status based on improved ResNeSt, Journal of Jilin University(Engineering and Technology Edition), 51, 2, pp. 704-711, (2021)
  • [4] Yu Y, Li X, Liu F., Attention GANs: unsupervised deep feature learning for aerial scene classification, IEEE Transactions on Geoscience and Remote Sensing, 58, 1, pp. 519-531, (2020)
  • [5] Lin D, Fu K, Wang Y, Et al., MARTA GANs: unsupervised representation learning for remote sensing image classification, IEEE Transactions on Geoscience and Remote Sensing, 14, 11, pp. 2092-2096, (2017)
  • [6] Geoffrey E H, Simon O, Yee-Whye T., A fast-learning algorithm for deep belief nets, Neural Computation, 18, 7, pp. 1527-1554, (2006)
  • [7] Diederik P K, Max W., Auto-encoding variational bayes[J]
  • [8] Chen T, Kornblith S, Norouzi M, Et al., A simple framework for contrastive learning of visual representations, Proceedings of the International Conference on Machine Learning, pp. 10709-10719, (2020)
  • [9] He K, Fan H, Wu Y, Et al., Momentum contrast for unsupervised visual representation learning[C], Proceedings of the Conference on Computer Vision and Pattern Recognition, pp. 9729-9738, (2020)
  • [10] He K, Zhang X, Ren S, Et al., Deep residual learning for image recognition, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770-778, (2016)
12