arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2211.02820cs.CVcs.LGeess.IV
收藏

一种鲁棒、低复杂度的遥感图像分类深度学习模型

A Robust and Low Complexity Deep Learning Model for Remote Sensing Image Classification

HCMC University of Technology(胡志明市理工大学);Austrian Institute of Technology(奥地利技术研究所);Pintel ltd.(Pintel有限公司)

Cam Le, Lam Pham, Nghia NVN, Truong Nguyen, Le Hong Trang

摘要:

在本文中,我们提出了一个强大的和低复杂度的深度学习模型,用于遥感图像分类(RSIC),识别遥感图像的场景的任务。特别是,我们首先评估了不同的低复杂度和基准深度神经网络:MobileNetV 1,MobileNetV 2,NASNetMobile和EfficientNetB 0,它们的可训练参数数量低于500万(M)。在指出最佳网络架构后,我们通过将注意力方案应用于从网络中间层提取的多个特征图来进一步提高网络性能。为了解决使用注意方案时增加模型占用空间的问题,我们应用量化技术来满足最大20 MB内存占用。通过在基准数据集NWPU-RESISC 45上进行广泛的实验,我们实现了一个鲁棒且低复杂度的模型,该模型与最先进的系统相比非常具有竞争力,并且具有在边缘设备上实际应用的潜力。

英文摘要:

In this paper, we present a robust and low complexity deep learning model for Remote Sensing Image Classification (RSIC), the task of identifying the scene of a remote sensing image. In particular, we firstly evaluate different low complexity and benchmark deep neural networks: MobileNetV1, MobileNetV2, NASNetMobile, and EfficientNetB0, which present the number of trainable parameters lower than 5 Million (M). After indicating best network architecture, we further improve the network performance by applying attention schemes to multiple feature maps extracted from middle layers of the network. To deal with the issue of increasing the model footprint as using attention schemes, we apply the quantization technique to satisfy the maximum of 20 MB memory occupation. By conducting extensive experiments on the benchmark datasets NWPU-RESISC45, we achieve a robust and low-complexity model, which is very competitive to the state-of-the-art systems and potential for real-life applications on edge devices.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑