Decision processes of computer vision models - especially deep neural networks - are opaque in nature, meaning that these decisions cannot be understood by humans. Thus, over the last years, many methods to provide human-understandable explanations have been proposed. For image classification, the most common group are saliency methods, which provide (super-)pixelwise feature attribution scores for input images. But their evaluation still poses a problem, as their results cannot be simply compared to the unknown ground truth. To overcome this, a slew of different proxy metrics have been defined, which are - as the explainability methods themselves - often built on intuition and thus, are possibly unreliable. In this paper, new evaluation metrics for saliency methods are developed and common saliency methods are benchmarked on ImageNet. In addition, a scheme for reliability evaluation of such metrics is proposed that is based on concepts from psychometric testing. The used code can be found at https://github.com/lelo204/ClassificationMetricsForImageExplanations .

翻译：计算机视觉模型（尤其是深度神经网络）的决策过程本质上是黑箱式的，这意味着人类无法理解这些决策。因此，近年来涌现出大量提供人类可理解解释的方法。对于图像分类任务，最常用的方法是显著性方法，这类方法为输入图像提供（超）像素级别的特征归因分数。然而，其评估仍存在问题，因为这些结果无法直接与未知的真实情况进行比较。为克服这一难题，研究者定义了一系列不同的代理指标——如同可解释性方法本身——这些指标通常基于直觉构建，因此可能存在不可靠性。本文针对显著性方法提出了新的评估指标，并在ImageNet数据集上对常见显著性方法进行了基准测试。此外，本文还提出了一种基于心理测量学概念的指标可靠性评估方案。相关代码可访问https://github.com/lelo204/ClassificationMetricsForImageExplanations 获取。