METHOD, COMPUTER PROGRAM AND DEVICE FOR EVALUATING THE ROBUSTNESS OF A NEURAL NETWORK AGAINST IMAGE DISTURBANCES

摘要

The invention relates to a method (100) for evaluating the robustness of a neural network (102) used for image processing against a group of at least two different disturbances that can be found in images, said method (100) comprising the following steps:determining a robustness score (SRIi), called individual robustness score, of said neural network (102) for each disturbance (Pi) in said group;determining at least one similarity score (SSIi,j), called individual similarity score, for the similarity between two disturbances in said group; andcalculating a robustness score (SRG), called overall robustness score, of said neural network (102) against said group of disturbances as a function of: the individual robustness scores (SRIi) for all the disturbances (P), andat least one individual similarity score (SSIi,j) for the similarity between two disturbances.;It also relates to a computer program and a device implementing such a method.