US 12,406,022 B2
Data augmentation for machine learning
Hiromi Kobayashi, Tokyo (JP); Masaharu Sakamoto, Tokyo (JP); Aya Nakashima, Tokyo (JP); Kazuya Hirayu, Tokyo (JP); and Sho Ikawa, Kanagawa-Ken (JP)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Nov. 18, 2021, as Appl. No. 17/455,514.
Prior Publication US 2023/0153383 A1, May 18, 2023
Int. Cl. G06F 18/00 (2023.01); G06F 18/214 (2023.01); G06V 10/46 (2022.01)
CPC G06F 18/214 (2023.01) [G06V 10/462 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A computer implemented method for training an image recognition model, the computer implemented method comprising:
creating, by a set of processor units, a saliency map of an original image; and
superimposing, by the set of processor units, the saliency map on the original image to form an augmented image, wherein the augmented image is used to train the image recognition model.