Author
Büyüktaş, Barış, Erdem, Ç. E., Erdem, Tanju
Publication Date
2021
Publication Place
-
IEEE
Subject
Curriculum learning, Deep learning, Face recognition
Type
Document
Language
English
Digital
Yes
Manuscript
No
Library
Özyeğin University
Library Asset ID
2076-1465
Record ID
76b63415-6eeb-4e31-870f-bf2dc602839a
Library Location
Computer Science
Date
2021
Sample Text
We present a novel curriculum learning (CL) algorithm for face recognition using convolutional neural networks. Curriculum learning is inspired by the fact that humans learn better, when the presented information is organized in a way that covers the easy concepts first, followed by more complex ones. It has been shown in the literature that that CL is also beneficial for machine learning tasks by enabling convergence to a better local minimum. In the proposed CL algorithm for face recognition, we divide the training set of face images into subsets of increasing difficulty based on the head pose angle obtained from the absolute sum of yaw, pitch and roll angles. These subsets are introduced to the deep CNN in order of increasing difficulty. Experimental results on the large-scale CASIA-WebFace-Sub dataset show that the increase in face recognition accuracy is statistically significant when CL is used, as compared to organizing the training data in random batches.
DOI
10.23919/Eusipco47968.2020.9287639
