论文标题
我们可以在深层生成网络中找到引起不切实际图像的神经元吗？
Can We Find Neurons that Cause Unrealistic Images in Deep Generative Networks?
论文作者
论文摘要
即使生成的对抗网络（GAN）表现出出色的产生高质量图像的能力，但甘恩并不总是保证产生的影像图。有时，它们会产生具有缺陷或不自然对象的图像，这些对象称为“工件”。研究这些伪影为什么出现这些伪像以及如何被检测和去除的研究尚未得到充分进行。为了分析这一点，我们首先假设很少激活的神经元和经常激活的神经元对生成图像的进展具有不同的目的和责任。在这项研究中，通过分析这些神经元的统计数据和作用，我们从经验上表明，很少激活的神经元与制造多种物体和诱导伪影的失败结果有关。此外，我们建议一种称为“顺序消融”的校正方法，以修复生成的图像的有缺陷部分，而无需高度的计算成本和手动努力。
Even though Generative Adversarial Networks (GANs) have shown a remarkable ability to generate high-quality images, GANs do not always guarantee the generation of photorealistic images. Occasionally, they generate images that have defective or unnatural objects, which are referred to as 'artifacts'. Research to investigate why these artifacts emerge and how they can be detected and removed has yet to be sufficiently carried out. To analyze this, we first hypothesize that rarely activated neurons and frequently activated neurons have different purposes and responsibilities for the progress of generating images. In this study, by analyzing the statistics and the roles for those neurons, we empirically show that rarely activated neurons are related to the failure results of making diverse objects and inducing artifacts. In addition, we suggest a correction method, called 'Sequential Ablation', to repair the defective part of the generated images without high computational cost and manual efforts.
