The sensitivity of image classifiers to small perturbations in the input is often viewed as a defect of their construction. We demonstrate that this sensitivity is a fundamental property of classifiers. For any arbitrary classifier over the set of $n$-by-$n$ images, we show that for all but one class it is possible to change the classification of all but a tiny fraction of the images in that class with a tiny modification compared to the diameter of the image space when measured in any $p$-norm, including the hamming distance. We then examine how this phenomenon manifests in human visual perception and discuss its implications for the design considerations of computer vision systems.
翻译:图像分类器对输入中小扰动的敏感度往往被视为其构造的缺陷。我们证明这种敏感度是分类器的基本属性。对于一组美元兑一美元图像的任何任意分类器来说,我们显示,除了一个类别之外,对于所有类别而言,除了一小部分图像外,都有可能改变该类别中所有图像的分类,与以任何摄氏度计时的图像空间直径相比,稍作改动,包括射线距离。我们然后研究这种现象如何表现在人类视觉感知中,并讨论其对计算机视觉系统设计考虑的影响。