论文标题
孔几何形状对镶嵌网络相对鲁棒性的影响：一项实证研究
The Impact of Hole Geometry on Relative Robustness of In-Painting Networks: An Empirical Study
论文作者
论文摘要
内贴网络使用现有像素来生成适当的像素，以填充图像部分上放置的“孔”。 2-D内部贴上网络的输入通常由（1）三通道2-D图像组成，（2）要在该图像中对“孔”进行的附加通道。在本文中，我们研究了给定的内部神经网络的鲁棒性，以防止孔几何分布的变化。我们观察到，在训练期间（在训练和测试中）没有改变，即使在训练过程中呈现孔几何形状的概率分布函数（PDF）也取决于孔几何形状的概率分布函数（PDF）。我们开发了一种实验方法，用于测试和评估针对四种不同类型的孔几何PDF的镶嵌网络的相对鲁棒性。我们检查了（1）关于训练的孔分布的自然偏差，（2）基础数据集将相对鲁棒性区分时，随着孔分布在火车测试（交叉检查）网格中的孔分布而变化，以及（3）（3）在holles和图像数据集中，（3）孔的方向分布的影响。我们介绍了L1，PSNR和SSIM质量指标的结果，并开发了基于这些质量指标的交叉比较网格中使用的相对贴上鲁棒性的特定度量。 （一个人可以在此相对度量中纳入其他质量指标。）此处报道的经验工作是对“填充空白”神经网络的敏感性，鲁棒性和对孔“几何” PDF的正则化的更广泛和更深入的研究的第一步，并且建议在该域中进行进一步的研究。
In-painting networks use existing pixels to generate appropriate pixels to fill "holes" placed on parts of an image. A 2-D in-painting network's input usually consists of (1) a three-channel 2-D image, and (2) an additional channel for the "holes" to be in-painted in that image. In this paper, we study the robustness of a given in-painting neural network against variations in hole geometry distributions. We observe that the robustness of an in-painting network is dependent on the probability distribution function (PDF) of the hole geometry presented to it during its training even if the underlying image dataset used (in training and testing) does not alter. We develop an experimental methodology for testing and evaluating relative robustness of in-painting networks against four different kinds of hole geometry PDFs. We examine a number of hypothesis regarding (1) the natural bias of in-painting networks to the hole distribution used for their training, (2) the underlying dataset's ability to differentiate relative robustness as hole distributions vary in a train-test (cross-comparison) grid, and (3) the impact of the directional distribution of edges in the holes and in the image dataset. We present results for L1, PSNR and SSIM quality metrics and develop a specific measure of relative in-painting robustness to be used in cross-comparison grids based on these quality metrics. (One can incorporate other quality metrics in this relative measure.) The empirical work reported here is an initial step in a broader and deeper investigation of "filling the blank" neural networks' sensitivity, robustness and regularization with respect to hole "geometry" PDFs, and it suggests further research in this domain.
