论文标题
游戏理论对错误分类的理解
Game-Theoretic Understanding of Misclassification
论文作者
论文摘要
本文从游戏理论观点分析了各种类型的图像错误分类。特别是，我们考虑对清洁，对抗和损坏的图像的错误分类，并通过分布多阶相互作用来表征它。我们发现，多阶相互作用的分布在错误分类的类型中各不相同。例如，错误分类的对抗图像比正确分类的清洁图像具有更高的高阶相互作用强度，这表明对抗性扰动会产生伪造特征，这是由像素之间复杂的合作引起的。相比之下，错误分类的损坏的图像的低阶相互作用强度低于正确分类的清洁图像，这表明损坏破坏了像素之间的本地合作。我们还使用相互作用对视觉变压器进行了首次分析。我们发现，视觉变压器在与CNN中的相互作用分布中显示出不同的趋势，这意味着它们利用了CNN不用于预测的特征。我们的研究表明，最近可以扩大对深度学习模型的游戏理论分析，以分析深度学习模型的各种故障，包括通过使用分布，顺序和相互作用的迹象。
This paper analyzes various types of image misclassification from a game-theoretic view. Particularly, we consider the misclassification of clean, adversarial, and corrupted images and characterize it through the distribution of multi-order interactions. We discover that the distribution of multi-order interactions varies across the types of misclassification. For example, misclassified adversarial images have a higher strength of high-order interactions than correctly classified clean images, which indicates that adversarial perturbations create spurious features that arise from complex cooperation between pixels. By contrast, misclassified corrupted images have a lower strength of low-order interactions than correctly classified clean images, which indicates that corruptions break the local cooperation between pixels. We also provide the first analysis of Vision Transformers using interactions. We found that Vision Transformers show a different tendency in the distribution of interactions from that in CNNs, and this implies that they exploit the features that CNNs do not use for the prediction. Our study demonstrates that the recent game-theoretic analysis of deep learning models can be broadened to analyze various malfunctions of deep learning models including Vision Transformers by using the distribution, order, and sign of interactions.
