论文标题
通过视觉辩论解释图像分类
Explaining Image Classification with Visual Debates
论文作者
论文摘要
获得对任何给定主题的不同观点的有效方法是进行辩论，参与者在其中主张和反对该主题。在这里，我们提出了一个新颖的辩论框架，用于理解和解释连续图像分类器的推理，以通过将其建模为多人序列零和辩论游戏来做出特定的预测。我们框架的对比性质鼓励玩家学会在辩论中提出各种各样的论点，探讨对手错过的推理踪迹，并突出分类器中的任何不确定性。具体而言，在我们提出的设置中，玩家提出的论点是从分类器离散的潜在知识中得出的，以支持或反对分类器的决定。由此产生的视觉辩论从分类器的离散潜在空间中收集了支持和相反的特征，作为分类器内部推理对其预测的内部推理的解释。我们在标准的评估指标（即忠诚和完整性）和新颖的指标中，对几何形状和MNIST数据集以及高分辨率动物面孔（AFHQ）数据集的视觉辩论以及高分辨率动物面孔（AFHQ）数据集进行了视觉辩论（AFHQ）数据集（即忠诚和完整性）和新颖的指标，以视觉辩论为解释（Cassensus and Cassensus and Cassensus and Cassensus and Cassensus and Cassensus和Nexpo）。
An effective way to obtain different perspectives on any given topic is by conducting a debate, where participants argue for and against the topic. Here, we propose a novel debate framework for understanding and explaining a continuous image classifier's reasoning for making a particular prediction by modeling it as a multiplayer sequential zero-sum debate game. The contrastive nature of our framework encourages players to learn to put forward diverse arguments during the debates, picking up the reasoning trails missed by their opponents and highlighting any uncertainties in the classifier. Specifically, in our proposed setup, players propose arguments, drawn from the classifier's discretized latent knowledge, to support or oppose the classifier's decision. The resulting Visual Debates collect supporting and opposing features from the discretized latent space of the classifier, serving as explanations for the internal reasoning of the classifier towards its predictions. We demonstrate and evaluate (a practical realization of) our Visual Debates on the geometric SHAPE and MNIST datasets and on the high-resolution animal faces (AFHQ) dataset, along standard evaluation metrics for explanations (i.e. faithfulness and completeness) and novel, bespoke metrics for visual debates as explanations (consensus and split ratio).
