Mode anomaly (MA for short) significantly blocks the application of generative adversarial networks (GANs). Although diverse metrics have been proposed to measure the MA, and a lot of efforts have been made to resolve the MA, none of them gives a quantitative definition for MA detection. Moreover, very few studies concentrate on the early-stage prediction of MA. In this paper, we make the first effort to this field with a systematic empirical study. To this end, we first give a fine-grained definition where the MA is categorized into three typical sub-patterns. Afterwards, traditional MA metrics are studied with extensive experiments on numbers of representative combinations of subjects (including 13 GANs and 3 datasets) to explore their sensitivity for the MA across different training steps. We find that in most of cases, the MA can be reasonably predicted in very early training stage through our sensitivity studies. Under the insight, we propose a novel prediction strategy using conception of “anomaly sign”. The evaluation results on diverse experimental subjects demonstrate the feasibility and high accuracy for the early prediction of MA. We also discuss the prediction efficiency, as well as analyze the prediction effectiveness from human perception.

模式异常（简称MA）显着阻碍了生成对抗网络（GAN）的应用。尽管已经提出了多种度量来测量MA，并且已经做出了很多努力来解决MA，但是它们都没有给出MA检测的定量定义。此外，很少有研究集中于MA的早期预测。在本文中，我们通过系统的实证研究对该领域做出了首次努力。为此，我们首先给出一个细粒度的定义，其中将MA分为三个典型的子模式。之后，通过对大量代表性代表（包括13个GAN和3个数据集）进行大量实验，研究了传统的MA指标，以探讨其在不同训练步骤中对MA的敏感性。我们发现在大多数情况下，通过我们的敏感性研究，可以在非常早期的培训阶段就合理地预测出MA。在这种见识之下，我们提出了一种使用“异常征兆”概念的新颖预测策略。对各种实验对象的评估结果证明了MA的早期预测的可行性和较高的准确性。我们还将讨论预测效率，并从人类感知中分析预测有效性。