Skip to yearly menu bar Skip to main content


Poster
in
Workshop: XAI in Action: Past, Present, and Future Applications

Assessment of the Reliablity of a Model's Decision by Generalizing Attribution to the Wavelet Domain

Gabriel Kasmi · Laurent Dubus · Yves-Marie Saint-Drenan · Philippe BLANC


Abstract:

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.

Chat is not available.