2020/04/03 by Shawn Xu, Subhashini Venugopalan, Xu, Shawn +3 · 3 citations
Computer Science · #Advanced Image Processing Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Image and Signal Denoising Methods #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE)
paper · pdf · doi:10.48550/arxiv.2004.03383
openalex publication_date 2020/04/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We study the attribution problem [28] for deep networks applied to perception tasks. For vision tasks, attribution techniques attribute the prediction of a network to the pixels of the input image. We propose a new technique called Blur Integrated Gradients. This technique has several advantages over other methods. First, it can tell at what scale a network recognizes an object. It produces scores in the scale/frequency dimension, that we find captures interesting phenomena. Second, it satisfies the scale-space axioms [14], which imply that it employs perturbations that are free of artifact. We therefore produce explanations that are cleaner and consistent with the operation of deep networks. Third, it eliminates the need for a 'baseline' parameter for Integrated Gradients [31] for perception tasks. This is desirable because the choice of baseline has a significant effect on the explanations. We compare the proposed technique against previous techniques and demonstrate application on three tasks: ImageNet object recognition, Diabetic Retinopathy prediction, and AudioSet audio event identification.