Training Convolutional Neural Networks with Multi-Size Images and Triplet Loss for Remote Sensing Scene Classification

Sensors

Zafer Al-Makhadmeh¹  Amr Tolba²  Jianming Zhang³  Chaoquan Lu³  Jin Wang³  Se-Jung Lim⁴  Xiao-Guang Yue⁵ 

[1] Convergence Studies, Honam University, Gwangju 62399, Korea;Computer Science Department, Community College, King Saud University, Riyadh 11437, Saudi Arabia;Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation, School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha 410114, China;;Liberal Arts &Rattanakosin International College of Creative Entrepreneurship, Rajamangala University of Technology Rattanakosin, Nakhon Pathom 73170, Thailand;

关键词: dropout;    triplet loss;    training with multi-size images;    remote sensing scene classification;   

DOI  :  10.3390/s20041188

来源: DOAJ

【 摘 要 】

Many remote sensing scene classification algorithms improve their classification accuracy by additional modules, which increases the parameters and computing overhead of the model at the inference stage. In this paper, we explore how to improve the classification accuracy of the model without adding modules at the inference stage. First, we propose a network training strategy of training with multi-size images. Then, we introduce more supervision information by triplet loss and design a branch for the triplet loss. In addition, dropout is introduced between the feature extractor and the classifier to avoid over-fitting. These modules only work at the training stage and will not bring about the increase in model parameters at the inference stage. We use Resnet18 as the baseline and add the three modules to the baseline. We perform experiments on three datasets: AID, NWPU-RESISC45, and OPTIMAL. Experimental results show that our model combined with the three modules is more competitive than many existing classification algorithms. In addition, ablation experiments on OPTIMAL show that dropout, triplet loss, and training with multi-size images improve the overall accuracy of the model on the test set by 0.53%, 0.38%, and 0.7%, respectively. The combination of the three modules improves the overall accuracy of the model by 1.61%. It can be seen that the three modules can improve the classification accuracy of the model without increasing model parameters at the inference stage, and training with multi-size images brings a greater gain in accuracy than the other two modules, but the combination of the three modules will be better.

【 授权许可】

Unknown