We present a set of metrics that utilize vision priors to effectively assess the performance of saliency methods on image classification tasks. To understand behavior in deep learning models, many methods provide visual saliency maps emphasizing image regions that most contribute to a model prediction. However, there is limited work on analyzing the reliability of saliency methods in explaining model decisions. We propose the metric COnsistency-SEnsitivity (COSE) that quantifies the equivariant and invariant properties of visual model explanations using simple data augmentations. Through our metrics, we show that although saliency methods are thought to be architecture-independent, most methods could better explain transformer-based models over convolutional-based models. In addition, GradCAM was found to outperform other methods in terms of COSE but was shown to have limitations such as lack of variability for fine-grained datasets. The duality between consistency and sensitivity allow the analysis of saliency methods from different angles. Ultimately, we find that it is important to balance these two metrics for a saliency map to faithfully show model behavior.

翻译：摘要：我们提出一组利用视觉先验有效评估图像分类任务中显著性方法性能的度量标准。为理解深度学习模型的行为，诸多方法通过视觉显著性图强调对模型预测贡献最大的图像区域。然而，目前关于分析显著性方法在解释模型决策时可靠性的研究仍十分有限。我们提出COSE（一致性-敏感性）度量，该度量通过简单数据增强量化视觉模型解释的等变与不变特性。通过我们的度量标准表明：尽管显著性方法被认为独立于网络架构，但多数方法在解释基于Transformer的模型时优于卷积模型。此外，GradCAM在COSE指标上表现最优，但存在细粒度数据集缺乏多样性的局限性。一致性与敏感性之间的对偶关系使我们能从多角度分析显著性方法。最终发现，为使显著性图忠实反映模型行为，平衡这两个指标至关重要。