公开(公告)号：US20250157201A1

公开(公告)日：2025-05-15

申请号：US19020516

申请日：2025-01-14

Applicant: Google LLC

Inventor： Arunachalam Narayanaswamy ,  Subhashini Venugopalan ,  Avinash Vaidyanathan Varadarajan

IPC: G06V10/776 ,  G06V10/82

Abstract: Systems and methods for identifying visual features that influence a predictive model are provided. The technology employs an image translation function to introduce a visual feature into an image to create a modified image that can be fed to a predictive model. When the predictive model generates a different prediction for a given image than it does for a modified version of that image, the image translation function can then be used to make further modified versions that exaggerate the introduced visual feature. The technology thus aids in identifying visual features that influence the predictive model so that the model's conclusions can be understood, and so that those visual features can be further studied and tested.

公开(公告)号：US12230016B2

公开(公告)日：2025-02-18

申请号：US17799740

申请日：2020-03-03

Applicant: Google LLC

Inventor： Arunachalam Narayanaswamy ,  Subhashini Venugopalan ,  Avinash Vaidyanathan Varadarajan

IPC: G06V10/776 ,  G06V10/82

Abstract: Systems and methods for identifying visual features that influence a predictive model are provided. The technology employs an image translation function to introduce a visual feature into an image to create a modified image that can be fed to a predictive model. When the predictive model generates a different prediction for a given image than it does for a modified version of that image, the image translation function can then be used to make further modified versions that exaggerate the introduced visual feature. The technology thus aids in identifying visual features that influence the predictive model so that the model's conclusions can be understood, and so that those visual features can be further studied and tested.