对抗学习遥感图像场景识别  

Remote sensing image scene recognition based on adversarial learning

作　　者：李彤 张钧萍[1] Li Tong;Zhang Junping(School of Electronics and Information Engineering,Harbin Institute of Technology,Harbin 150001,China;Shanghai Institute of Satellite Engineering,Shanghai 201109,China)

机构地区：[1]哈尔滨工业大学电子与信息工程学院,哈尔滨150001 [2]上海卫星工程研究所,上海201109

出　　处：《中国图象图形学报》2021年第11期2732-2740,共9页Journal of Image and Graphics

基　　金：国家自然科学基金项目(61871150)。

摘　　要：目的在高分辨率遥感图像场景识别问题中,经典的监督机器学习算法大多需要充足的标记样本训练模型,而获取遥感图像的标注费时费力。为解决遥感图像场景识别中标记样本缺乏且不同数据集无法共享标记样本问题,提出一种结合对抗学习与变分自动编码机的迁移学习网络。方法利用变分自动编码机(variational autoencoders,VAE)在源域数据集上进行训练,分别获得编码器和分类器网络参数,并用源域编码器网络参数初始化目标域编码器。采用对抗学习的思想,引入判别网络,交替训练并更新目标域编码器与判别网络参数,使目标域与源域编码器提取的特征尽量相似,从而实现遥感图像源域到目标域的特征迁移。结果利用两个遥感场景识别数据集进行实验,验证特征迁移算法的有效性,同时尝试利用SUN397自然场景数据集与遥感场景间的迁移识别,采用相关性对齐以及均衡分布适应两种迁移学习方法作为对比。两组遥感场景数据集间的实验中,相比于仅利用源域样本训练的网络,经过迁移学习后的网络场景识别精度提升约10%,利用少量目标域标记样本后提升更为明显;与对照实验结果相比,利用少量目标域标记样本时提出方法的识别精度提升均在3%之上,仅利用源域标记样本时提出方法场景识别精度提升了10%40%;利用自然场景数据集时,方法仍能在一定程度上提升场景识别精度。结论本文提出的对抗迁移学习网络可以在目标域样本缺乏的条件下,充分利用其他数据集中的样本信息,实现不同场景图像数据集间的特征迁移及场景识别,有效提升遥感图像的场景识别精度。Objective While dealing with high-resolution remote sensing image scene recognition,classical supervised machine learning algorithms are considered effective on two conditions,namely,1)test samples should be in the same feature space with training samples,and 2)adequate labeled samples should be provided to train the model fully.Deep learning algorithms,which achieve remarkable results in image classification and object detection for the past few years,generally require a large number of labeled samples to learn the accurate parameters.The main image classification methods select training and test samples randomly from the same dataset,and adopt cross validation to testify the effectiveness of the model.However,obtaining scene labels is time consuming and expensive for remote sensing images.To deal with the insufficiency of labeled samples in remote sensing image scene recognition and the problem that labeled samples cannot be shared between different datasets due to different sensors and complex light conditions,deep learning architecture and adversarial learning are investigated.A feature transfer method based on adversarial variational autoencoder(VAE)is proposed.Method Feature transfer architecture can be divided into three parts.The first part is the pretrain module.Given the limited samples with scene labels,the unsupervised learning model,VAE,is adopted.The VAE is unsupervised trained on the source dataset,and the encoder part in the VAE is finetuned together with classifier network using labeled samples in the source dataset.The second part is adversarial learning module.In most of the research,adversarial learning is adopted to generate new samples,while the idea is used to transfer the features from source domain to target domain in this paper.Parameters of the finetuned encoder network for the source dataset are then used to initialize the target encoder.Using the idea of adversarial training in generative adversarial networks(GAN),a discrimination network is introduced into the training of the target

关 键 词：场景识别 遥感图像 对抗学习 迁移学习 变分自动编码机(VAE) 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]