Patent · US Active

System and methods for active domain adaptation

US12380679B2 · kind B2 · utility

0Cited by

1References

20Claims

0Family size

Assignee

Adobe Inc. · US

Inventors

Divya Kothandaraman · College Park, US
Sumit Shekhar · Bengaluru, IN
Abhilasha Sancheti · College Park, US
Manoj Ghuhan Arivazhagan · Komangalam, IN
Tripti Shukla · Lucknow, IN

Key dates

Filing date	Jan 20, 2022
Grant date	Aug 5, 2025
Priority date	—
Expiry date	Mar 25, 2044

Classification

Technology area (CPC G)Physics
CPC primaryG06V10/82
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Systems and methods for machine learning are described. The systems and methods include 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, and updating parameters of the target network based on the attention map and the ground truth label data.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.