论文标题
通过放大域差异来定位非火山区域
Inharmonious Region Localization by Magnifying Domain Discrepancy
论文作者
论文摘要
非火山区域的定位旨在将该区域定位在与周围背景不相容的合成图像中。非武器问题主要归因于图像编辑技术产生的颜色和照明不一致。在这项工作中，我们倾向于将输入图像转换为另一个颜色空间，以放大非火山区域和背景之间的域差异，以便模型可以更轻松地识别非火山区域。为此，我们提出了一个新的框架，该框架由一个颜色映射模块和一个非火山区域定位网络组成，其中前者配备了新型的域差异放大损失，而后者可能是任意的定位网络。图像协调数据集的广泛实验显示了我们设计框架的优越性。我们的代码可在https://github.com/bcmi/madisnet-inharmonious-gregion-localization上找到。
Inharmonious region localization aims to localize the region in a synthetic image which is incompatible with surrounding background. The inharmony issue is mainly attributed to the color and illumination inconsistency produced by image editing techniques. In this work, we tend to transform the input image to another color space to magnify the domain discrepancy between inharmonious region and background, so that the model can identify the inharmonious region more easily. To this end, we present a novel framework consisting of a color mapping module and an inharmonious region localization network, in which the former is equipped with a novel domain discrepancy magnification loss and the latter could be an arbitrary localization network. Extensive experiments on image harmonization dataset show the superiority of our designed framework. Our code is available at https://github.com/bcmi/MadisNet-Inharmonious-Region-Localization.
