Invention Grant
- Patent Title: Unsupervised cross-domain distance metric adaptation with feature transfer network
-
Application No.: US16400429Application Date: 2019-05-01
-
Publication No.: US10885383B2Publication Date: 2021-01-05
- Inventor: Kihyuk Sohn , Manmohan Chandraker , Xiang Yu
- Applicant: NEC Laboratories America, Inc.
- Applicant Address: US NJ Princeton
- Assignee: NEC Laboratories America, Inc.
- Current Assignee: NEC Laboratories America, Inc.
- Current Assignee Address: US NJ Princeton
- Agent Joseph Kolodka
- Main IPC: G06K9/62
- IPC: G06K9/62 ; G06N20/20 ; G06K9/00

Abstract:
A method for implementing an unsupervised cross-domain distance metric adaptation framework with a feature transfer network for enhancing facial recognition includes recursively training a feature transfer network and automatic labeling of target domain data using a clustering method, and implementing the feature transfer network and the automatic labeling to perform a facial recognition task.
Public/Granted literature
- US20190354801A1 UNSUPERVISED CROSS-DOMAIN DISTANCE METRIC ADAPTATION WITH FEATURE TRANSFER NETWORK Public/Granted day:2019-11-21
Information query