2023/05/24 by Gabriel Kasmi, Laurent Dubus, Kasmi, Gabriel +5
Computer Science · Biochemistry, Genetics and Molecular Biology · #Adversarial Robustness in Machine Learning #Explainable Artificial Intelligence (XAI) #Cell Image Analysis Techniques
paper · pdf · doi:10.48550/arxiv.2305.14979
Neural networks have shown remarkable performance in computer vision, but their deployment in numerous scientific and technical fields is challenging due to their black-box nature. Scientists and practitioners need to evaluate the reliability of a decision, i.e., to know simultaneously if a model relies on the relevant features and whether these features are robust to image corruptions. Existing attribution methods aim to provide human-understandable explanations by highlighting important regions in the image domain, but fail to fully characterize a decision process's reliability. To bridge this gap, we introduce the Wavelet sCale Attribution Method (WCAM), a generalization of attribution from the pixel domain to the space-scale domain using wavelet transforms. Attribution in the wavelet domain reveals where and on what scales the model focuses, thus enabling us to assess whether a decision is reliable. Our code is accessible here: \urlhttps://github.com/gabrielkasmi/spectral-attribution.