arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.09322cs.CVcs.LGeess.IV
收藏

基于形态分割的领域自适应

Domain Adaptation with Morphologic Segmentation

University of Bonn(波恩大学);Google Brain(谷歌大脑);KAUST(阿卜杜拉国王科技大学)

Jonathan Klein, Sören Pirk, Dominik L. Michels

摘要:

我们提出了一种新的领域自适应框架,使用形态分割转换图像从任意输入域(真实和合成)到一个统一的输出域。我们的框架是基于一个既定的图像到图像的翻译管道,使我们能够首先将输入图像转换成一个广义的表示,编码形态和语义-边缘加分割图(EPS)-然后转换到一个输出域。转换到输出域的图像具有照片般的真实感,并且没有通常存在于不同真实图像中的伪影(例如镜头光斑、运动模糊等)。和合成(例如,不现实的纹理,简化的几何形状等)数据集。我们的目标是建立一个预处理步骤,将来自多个来源的数据统一为一个通用的表示,以促进计算机视觉中的下游任务的训练。通过这种方式,用于现有任务的神经网络可以在更大范围的训练数据上进行训练,同时它们也较少受到特定数据集过拟合的影响。我们展示了我们的方法的有效性,定性和定量评估我们的方法对四个数据集的模拟和真实的城市场景数据。其他结果可在项目网站http://jonathank.de/research/eps/上查阅。

英文摘要:

We present a novel domain adaptation framework that uses morphologic segmentation to translate images from arbitrary input domains (real and synthetic) into a uniform output domain. Our framework is based on an established image-to-image translation pipeline that allows us to first transform the input image into a generalized representation that encodes morphology and semantics - the edge-plus-segmentation map (EPS) - which is then transformed into an output domain. Images transformed into the output domain are photo-realistic and free of artifacts that are commonly present across different real (e.g. lens flare, motion blur, etc.) and synthetic (e.g. unrealistic textures, simplified geometry, etc.) data sets. Our goal is to establish a preprocessing step that unifies data from multiple sources into a common representation that facilitates training downstream tasks in computer vision. This way, neural networks for existing tasks can be trained on a larger variety of training data, while they are also less affected by overfitting to specific data sets. We showcase the effectiveness of our approach by qualitatively and quantitatively evaluating our method on four data sets of simulated and real data of urban scenes. Additional results can be found on the project website available at http://jonathank.de/research/eps/ .

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑