Guided Integrated Gradients: an Adaptive Path Method for Removing Noise
Guided Integrated Gradients: an Adaptive Path Method for Removing Noise
Integrated Gradients (IG) [29] is a commonly used feature attribution method for deep neural networks. While IG has many desirable properties, the method often produces spurious/noisy pixel attributions in regions that are not related to the predicted class when applied to visual models. While this has been previously noted [27], …