论文标题
从歧视者的角度解释Galaxy Deblender Gan
Interpreting Galaxy Deblender GAN from the Discriminator's Perspective
论文作者
论文摘要
生成的对抗网络（GAN）以其无监督的学习能力而闻名。天文学领域的最新成功是通过分支的GAN模型拆除了两个重叠的星系图像。但是，理解网络的工作原理仍然是一个重大挑战，这对于非专家用户来说尤其困难。这项研究的重点是该网络主要组成部分之一的行为，即歧视者，它起着至关重要的作用，但经常被忽略，具体来说，我们增强了层面相关性传播（LRP）方案，以生成基于热图的可视化。我们称此技术极化-lrp，它由两个部分组成，即地面真相图像的积极贡献热图和产生的图像的负贡献热图。使用Galaxy Zoo数据集，我们证明了我们的方法清楚地揭示了歧视者的注意力区域，而当将生成的星系图像与地面真相图像区分开时。为了连接鉴别器对发电机的影响，我们可以在整个训练过程中可视化发电机的逐渐变化。一个有趣的结果，我们已经实现了有问题的数据增强程序的检测，而该过程仍然隐藏了。我们发现我们提出的方法是一种有用的视觉分析工具，可深入了解GAN模型。
Generative adversarial networks (GANs) are well known for their unsupervised learning capabilities. A recent success in the field of astronomy is deblending two overlapping galaxy images via a branched GAN model. However, it remains a significant challenge to comprehend how the network works, which is particularly difficult for non-expert users. This research focuses on behaviors of one of the network's major components, the Discriminator, which plays a vital role but is often overlooked, Specifically, we enhance the Layer-wise Relevance Propagation (LRP) scheme to generate a heatmap-based visualization. We call this technique Polarized-LRP and it consists of two parts i.e. positive contribution heatmaps for ground truth images and negative contribution heatmaps for generated images. Using the Galaxy Zoo dataset we demonstrate that our method clearly reveals attention areas of the Discriminator when differentiating generated galaxy images from ground truth images. To connect the Discriminator's impact on the Generator, we visualize the gradual changes of the Generator across the training process. An interesting result we have achieved there is the detection of a problematic data augmentation procedure that would else have remained hidden. We find that our proposed method serves as a useful visual analytical tool for a deeper understanding of GAN models.
