To better understand the behavior of image classifiers, it is useful to
visualize the contribution of individual pixels to the model prediction. In
this study, we propose a method, MoXI~($\textbf{Mo}$del e$\textbf{X}$planation
by $\textbf{I}$nteractions), that efficiently and accurately identifies a group
of pixels with high prediction confidence. The proposed method employs
game-theoretic concepts, Shapley values and interactions, taking into account
the effects of individual pixels and the cooperative influence of pixels on
model confidence. Theoretical analysis and experiments demonstrate that our
method better identifies the pixels that are highly contributing to the model
outputs than widely-used visualization methods using Grad-CAM, Attention
rollout, and Shapley value. While prior studies have suffered from the
exponential computational cost in the computation of Shapley value and
interactions, we show that this can be reduced to linear cost for our task.

为了更好地理解图像分类器的行为，本研究提出了一种方法 MoXI（模型交互解释），该方法通过有效且准确地识别一组具有高预测置信度的像素，采用了博弈论的概念、Shapley 值和像素之间的相互影响，既考虑了个别像素的影响，又考虑了像素对模型置信度的合作影响。理论分析和实验证明了我们的方法相比使用 Grad-CAM、Attention 展开和 Shapley 值的广泛使用的可视化方法更好地识别出对模型输出有高度贡献的像素。而之前的研究在计算 Shapley 值和交互作用时遇到了指数级计算成本的问题，我们在本研究中证明了这可以降低到线性成本。