公开(公告)号：US11961287B2

公开(公告)日：2024-04-16

申请号：US17449872

申请日：2021-10-04

申请人： ServiceNow Canada Inc.

发明人： Pau Rodriguez Lopez ,  Massimo Caccia ,  Lee Zamparo ,  Issam Laradji ,  Alexandre Lacoste ,  David Vazquez Bermudez

IPC分类号： G06V10/98 ,  G06T5/50 ,  G06V10/44 ,  G06V10/46 ,  G06V10/82

CPC分类号： G06V10/98 ,  G06T5/50 ,  G06V10/454 ,  G06V10/473 ,  G06V10/82

摘要： A computer-implemented method for explaining an image classifier, the method comprising: receiving an initial image, the initial image having been wrongly classified by the image classifier; receiving an initial gradient of a function executed by the image classifier generated while classifying the initial image, the function being indicative of a probability for the initial image to belong to an initial class; converting the initial image into a latent vector, the latent vector being a representation of the initial image in a latent space; generating a plurality of perturbation vectors using the initial gradient of the function executed by the image classifier; combining the latent vector with each one of the plurality of perturbation vectors, thereby obtaining a plurality of modified vectors; for each one of the plurality of modified vectors, reconstructing a respective image, thereby obtaining a plurality of reconstructed images; transmitting the reconstructed images to the image classifier; for each one of the plurality of reconstructed images, receiving a respective updated gradient of the function executed by the image classifier; using the respective updated gradients, determining amongst the reconstructed images at least one given reconstructed image for which the respective updated gradient is indicative that a new class different from the initial class has been assigned by the image classifier; and outputting the at least one given reconstructed image.