Patent · US Active

L2 constrained softmax loss for discriminative face verification

US11636328B2 · kind B2 · utility

1Cited by

0References

12Claims

0Family size

Assignee

UNIVERSITY OF MARYLAND, COLLEGE PARK · US

Inventors

Rajeev Ranjan · College Park, US
Carlos Castillo · Seattle, US
Ramalingam Chellappa · Potomac, US

Key dates

Filing date	Mar 28, 2018
Grant date	Apr 25, 2023
Priority date	—
Expiry date	Nov 16, 2041

Classification

Technology area (CPC G)Physics
CPC primaryG06V40/172
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Various face discrimination systems may benefit from techniques for providing increased accuracy. For example, certain discriminative face verification systems can benefit from L2-constrained softmax loss. A method can include applying an image of a face as an input to a deep convolutional neural network. The method can also include applying an output of a fully connected layer of the deep convolutional neural network to an L2-normalizing layer. The method can further include determining softmax loss based on an output of the L2-normalizing layer.

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