| 基于生成对抗网络的半监督遥感图像飞机检测 |
| |
| 作者姓名： | 陈国炜 刘磊 郭嘉逸 潘宗序 胡文龙 |
| |
| 作者单位： | 1. 中国科学院电子学研究所 中国科学院空间信息处理与应用系统技术重点实验室, 北京 100190;
2. 中国科学院大学, 北京 100049 |
| |
| 基金项目： | 国家自然科学基金（61701478）资助 |
| |
| 摘 要： | 遥感图像上的飞机目标检测是一件极富挑战性的工作，吸引了广大研究者的兴趣。基于人工神经网络的方法是当前遥感图像飞机目标检测的主流方法，这类方法要求人工标记大量的数据用于训练。对训练图像的人工标注工作费时费力，是制约有效利用大规模数据的主要瓶颈之一。为解决这个问题，提出一种基于生成对抗网络（generative adversarial networks，GAN）的半监督检测方法。在遥感图像飞机目标检测中，该方法不需要标记全部用于训练的图像，只需要标记其中一小部分样本，再和大量未标记数据一起进行训练便能取得优异的检测结果。该方法结合传统的检测网络和基于GAN的半监督学习网络。在对抗训练过程中，生成器学习数据分布并生成假样本，判别器判别真假样本，同时判别器还需要从标记数据中学习类别信息。最后，判别器学习到的决策分类面不仅仅区分出标记数据，而且平行于数据分布的边界。实验证明，在存在大量可供训练的图像的基础上，减少标注数据的比例，全监督学习方法性能会大幅下降；而本文提出的半监督学习方法，由于利用了未标注的数据，能保持更好的检测性能。
|
| 关 键 词： | 半监督学习 生成对抗网络 目标检测 |
| 收稿时间： | 2018-12-18 |
| 修稿时间： | 2019-03-27 |
Semi-supervised airplane detection in remote sensing images using generative adversarial networks |
| |
| Authors: | CHEN Guowei LIU Lei GUO Jiayi PAN Zongxu HU Wenlong |
| |
| Institution: | 1. Key Laboratory of Spatial Information Processing and Application System Technology of CAS, Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, China;
2. University of Chinese Academy of Sciences, Beijing 100049, China |
| |
| Abstract: | Airplane detection in remote sensing images is a challenging task and researchers have been sparing no efforts in making breakthroughs in this topic. The methods based on artificial neural network are the main methods for airplane detection in remote sensing images. However, a large number of data must be annotated for training, which is time-consuming. This is one of the main bottlenecks to limit large-scale data to be effectively used. To address this problem, a generative adversarial networks (GAN)-based semi-supervised object detection method is proposed in this work. In airplane detection in remote sensing images, the method does not need to annotate all of the images, but only a small part of them, and then trains them together with a large number of unannotated data to achieve excellent detection performance. The proposed method combines a traditional detection network with a semi-supervised learning network based on GAN. During the adversarial training procedure, the generator learns the data distribution and generates fake samples, while the discriminator distinguishes between the true samples and the generated fake samples. At the same time, the discriminator is also trained on labeled data. Finally, the discriminator learns the decision boundary that not only separates labeled samples, but also parallels with the distribution boundary of the whole data. Experiments show that, with a large number of images, reducing the proportion of labeled data will significantly reduce the performance of the full-supervised learning method, while the semi-supervised learning method proposed in this work maintains the detection performance due to the use of unlabeled data. |
| |
| Keywords: | semi-supervised learning generative adversarial networks (GAN) object detection |
|
| 点击此处可从《》浏览原始摘要信息 |
| 点击此处可从《》下载免费的PDF全文 |
|
