当前位置: X-MOL 学术IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Semantic Segmentation of Remote Sensing Images With Self-Supervised Multitask Representation Learning
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing ( IF 5.5 ) Pub Date : 2021-06-18 , DOI: 10.1109/jstars.2021.3090418
Wenyuan Li , Hao Chen , Zhenwei Shi

Existing deep learning-based remote sensing images semantic segmentation methods require large-scale labeled datasets. However, the annotation of segmentation datasets is often too time-consuming and expensive. To ease the burden of data annotation, self-supervised representation learning methods have emerged recently. However, the semantic segmentation methods need to learn both high-level and low-level features, but most of the existing self-supervised representation learning methods usually focus on one level, which affects the performance of semantic segmentation for remote sensing images. In order to solve this problem, we propose a self-supervised multitask representation learning method to capture effective visual representations of remote sensing images. We design three different pretext tasks and a triplet Siamese network to learn the high-level and low-level image features at the same time. The network can be trained without any labeled data, and the trained model can be fine-tuned with the annotated segmentation dataset. We conduct experiments on Potsdam, Vaihingen dataset, and cloud/snow detection dataset Levir_CS to verify the effectiveness of our methods. Experimental results show that our proposed method can effectively reduce the demand of labeled datasets and improve the performance of remote sensing semantic segmentation. Compared with the recent state-of-the-art self-supervised representation learning methods and the mostly used initialization methods (such as random initialization and ImageNet pretraining), our proposed method has achieved the best results in most experiments, especially in the case of few training data. With only 10% to 50% labeled data, our method can achieve the comparable performance compared with random initialization. Codes are available at https://github.com/flyakon/SSLRemoteSensing .

中文翻译:

具有自监督多任务表示学习的遥感图像语义分割

现有的基于深度学习的遥感图像语义分割方法需要大规模标记数据集。然而,分割数据集的注释往往过于耗时和昂贵。为了减轻数据注释的负担,最近出现了自监督表示学习方法。然而,语义分割方法需要同时学习高层次和低层次的特征,而现有的自监督表示学习方法大多集中在一个层次上,这影响了遥感图像语义分割的性能。为了解决这个问题,我们提出了一种自监督的多任务表示学习方法来捕获遥感图像的有效视觉表示。我们设计了三个不同的借口任务和一个三元组连体网络来同时学习高级和低级图像特征。可以在没有任何标记数据的情况下训练网络,并且可以使用带注释的分割数据集对训练后的模型进行微调。我们在 Potsdam、Vaihingen 数据集和云/雪检测数据集 Levir_CS 上进行实验,以验证我们方法的有效性。实验结果表明,我们提出的方法可以有效减少对标记数据集的需求,提高遥感语义分割的性能。与最近最先进的自监督表示学习方法和最常用的初始化方法(如随机初始化和 ImageNet 预训练)相比,我们提出的方法在大多数实验中都取得了最好的结果,特别是在训练数据很少的情况下。只有 10% 到 50% 的标记数据,我们的方法可以达到与随机初始化相当的性能。代码可在https://github.com/flyakon/SSLRemoteSensing .
更新日期:2021-07-16
down
wechat
bug