Guided Integrated Gradients: An Adaptive Path Method for Removing Noise

Integrated Gradients (IG) is a commonly used feature attribution method for deep neural networks. While IG has many desirable properties, when applied to visual models, the method often produces spurious/noisy pixel attributions in regions that are not related to the predicted class. While this has been previously noted, most existing solutions are aimed at addressing the symptoms by explicitly reducing the noise in the resulting attributions. In this work, we show that one of the causes of the problem is the presence of "adversarial examples'' along the IG path. To minimize the effect of adversarial examples on attributions, we propose adapting the attribution path itself. We introduce Adaptive Path Methods (APMs), as a generalization of path methods, and Guided IG as a specific instance of an APM. Empirically, Guided IG creates saliency maps better aligned with the model's prediction and the input image that is being explained. We show through qualitative and quantitative experiments that Guided IG outperforms IG on ImageNet, Open Images, and diabetic retinopathy medical images.

• Machine Intelligence

• Machine Perception