US 12,380,679 B2
System and methods for active domain adaptation
Divya Kothandaraman, College Park, MD (US); Sumit Shekhar, Bengaluru (IN); Abhilasha Sancheti, Rajasthan (IN); Manoj Ghuhan Arivazhagan, Tamil Nadu (IN); and Tripti Shukla, Uttar Pradesh (IN)
Assigned to ADOBE INC., San Jose, CA (US)
Filed by ADOBE INC., San Jose, CA (US)
Filed on Jan. 20, 2022, as Appl. No. 17/648,482.
Prior Publication US 2023/0230358 A1, Jul. 20, 2023
Int. Cl. G06V 10/774 (2022.01); G06V 10/776 (2022.01); G06V 10/778 (2022.01); G06V 10/82 (2022.01)
CPC G06V 10/774 (2022.01) [G06V 10/776 (2022.01); G06V 10/778 (2022.01); G06V 10/82 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving target training data including a training image and ground truth label data for the training image;
generating source network features for the training image using a source network trained on source training data;
generating target network features for the training image using a target network;
generating at least one attention map for training the target network based on the source network features and the target network features using a guided attention transfer network, wherein the at least one attention map indicates regions or channels of the source network features that align with corresponding regions or channels of the target network features; and
updating parameters of the target network based on the attention map and the ground truth label data.