Removing Brightness Bias in Rectified Gradients
share
Interpretation and improvement of deep neural networks relies on better understanding of their underlying mechanisms. In particular, gradients of classes or concepts with respect to the input features (e.g., pixels in images) are often used as importance scores, which are visualized in saliency maps. Thus, a family of saliency methods provide an intuitive way to identify input features with substantial influences on classifications or latent concepts. Rectified Gradients <cit.> is a new method which introduce layer-wise thresholding in order to denoise the saliency maps. While visually coherent in certain cases, we identify a brightness bias in Rectified Gradients. We demonstrate that dark areas of an input image are not highlighted by a saliency map using Rectified Gradients, even if it is relevant for the class or concept. Even in the scaled images, the bias exists around an artificial point in color spectrum. Our simple modification removes this bias and recovers input features that were removed due to their colors. "No Bias Rectified Gradient" is available at <https://github.com/lenbrocki/NoBias-Rectified-Gradient>
READ FULL TEXT