US 12,230,016 B2
Explanation of machine-learned models using image translation
Arunachalam Narayanaswamy, Sunnyvale, CA (US); Subhashini Venugopalan, Mountain View, CA (US); and Avinash Vaidyanathan Varadarajan, Los Altos, CA (US)
Assigned to Google LLC, Mountain View, CA (US)
Appl. No. 17/799,740
Filed by Google LLC, Mountain View, CA (US)
PCT Filed Mar. 3, 2020, PCT No. PCT/US2020/020773
§ 371(c)(1), (2) Date Aug. 15, 2022,
PCT Pub. No. WO2021/177943, PCT Pub. Date Sep. 10, 2021.
Prior Publication US 2023/0108319 A1, Apr. 6, 2023
Int. Cl. G06V 10/776 (2022.01); G06V 10/82 (2022.01)
CPC G06V 10/776 (2022.01) [G06V 10/82 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for identifying visual features impacting model prediction, the method comprising:
generating, by one or more processors of a processing system, a first prediction based on a first image using a predictive model;
generating, by the one or more processors, a second prediction based on a second image using the predictive model, wherein the second image includes a visual feature created by modifying at least a portion of the first image using a translation function, and the second prediction is different than the first prediction; and
modifying, by the one or more processors, at least a portion of the second image using the translation function to create a third image in which the visual feature is amplified relative to the second image;
wherein the translation function is configured to translate a first class of imagery to appear more like a second class of imagery.