Neural Networks are sensitive to various corruptions that usually occur in real-world applications such as blurs, noises, low-lighting conditions, etc. To estimate the robustness of neural networks to these common corruptions, we generally use a group of modeled corruptions gathered into a benchmark. Unfortunately, no objective criterion exists to determine whether a benchmark is representative of a large diversity of independent corruptions. In this paper, we propose a metric called corruption overlapping score, which can be used to reveal flaws in corruption benchmarks. Two corruptions overlap when the robustnesses of neural networks to these corruptions are correlated. We argue that taking into account overlappings between corruptions can help to improve existing benchmarks or build better ones.
翻译:神经网络对通常在现实世界应用中发生的各种腐败十分敏感,如模糊、噪音、低光度条件等。 为了估计神经网络对这些常见腐败的稳健性,我们通常使用一组模型化的腐败收集成基准。不幸的是,没有客观标准来确定基准是否代表了各种各样的独立腐败。在本文中,我们提出了一个称为腐败重叠得分的衡量标准,可用于揭示腐败基准的缺陷。当神经网络的稳健性与这些腐败相关时,两种腐败重叠。我们争论说,考虑到腐败之间的重叠有助于改进现有基准或建立更好的基准。