论文标题
无监督的图像产生增强了热图像中对象检测的适应性
Unsupervised Image-generation Enhanced Adaptation for Object Detection in Thermal images
论文作者
论文摘要
热图像中的对象检测是一项重要的计算机视觉任务，并且具有许多应用程序，例如无人车，机器人技术，监视和夜视。基于深度学习的探测器已取得了重大进展，通常需要大量标记的培训数据。但是，在热图像中标记为对象检测的数据稀缺，收集昂贵。如何利用标有可见图像的大数量并将其调整到热图像域中，预计将解决。本文提出了一种无监督的图像生成增强的适应方法，用于在热图像中检测对象检测。为了减少可见的域和热域之间的差距，提出的方法设法生成了与目标图像相似的模拟假热图像，并保留可见源域的注释信息。图像生成包括基于自行车的图像到图像翻译和强度反转变换。生成的假热图像用作更新的源域。然后利用现成的域自适应更快的RCNN来减少生成的中间域和热目标域之间的差距。实验证明了所提出的方法的有效性和优势。
Object detection in thermal images is an important computer vision task and has many applications such as unmanned vehicles, robotics, surveillance and night vision. Deep learning based detectors have achieved major progress, which usually need large amount of labelled training data. However, labelled data for object detection in thermal images is scarce and expensive to collect. How to take advantage of the large number labelled visible images and adapt them into thermal image domain, is expected to solve. This paper proposes an unsupervised image-generation enhanced adaptation method for object detection in thermal images. To reduce the gap between visible domain and thermal domain, the proposed method manages to generate simulated fake thermal images that are similar to the target images, and preserves the annotation information of the visible source domain. The image generation includes a CycleGAN based image-to-image translation and an intensity inversion transformation. Generated fake thermal images are used as renewed source domain. And then the off-the-shelf Domain Adaptive Faster RCNN is utilized to reduce the gap between generated intermediate domain and the thermal target domain. Experiments demonstrate the effectiveness and superiority of the proposed method.
