NDLI: Improved softmax loss for deep learning-based face and expression recognition

Please wait, while we are loading the content...

Biosurface and Biotribology

CAAI Transactions on Intelligence Technology

CIRED - Open Access Proceedings Journal

Chinese Journal of Electronics

Cognitive Computation and Systems

Volume 3 (2021)

Volume 2 (2020)

Volume 1 (2019)

Volume 1 (2019) : Issue 4, Dec

Cognitive science and artificial intelligence: simulating the human mind and its complexity

Disentanglement in conceptual space during sensorimotor interaction

Gender identification based on human brain structural MRI with a multi-layer 3D convolution extreme learning machine

Improved softmax loss for deep learning-based face and expression recognition

Volume 1 (2019) : Issue 3, Sep

Volume 1 (2019) : Issue 2, Jul

Volume 1 (2019) : Issue 1, Mar

Electronics Letters

Energy Conversion and Economics

Engineering & Technology

Engineering Biology

Healthcare Technology Letters

IET Circuits, Devices & Systems

IET Collaborative Intelligent Manufacturing

IET Communications

IET Computer Vision

IET Computers & Digital Techniques

IET Control Theory & Applications

IET Cyber-Physical Systems: Theory & Applications

IET Cyber-Systems and Robotics

IET Electric Power Applications

IET Electrical Systems in Transportation

IET Energy Systems Integration

IET Generation, Transmission & Distribution

IET Image Processing

IET Information Security

IET Intelligent Transport Systems

IET Microwaves, Antennas & Propagation

IET Nanobiotechnology

IET Nanodielectrics

IET Optoelectronics

IET Power Electronics

IET Quantum Communication

IET Radar, Sonar & Navigation

IET Renewable Power Generation

IET Science, Measurement & Technology

IET Signal Processing

IET Smart Cities

IET Systems Biology

IET Wireless Sensor Systems

Micro & Nano Letters

The Journal of Engineering

Improved softmax loss for deep learning-based face and expression recognition

Content Provider	IET Digital Library
Author	Zhou, Jiancan Jia, Xi Shen, Linlin Wen, Zhenkun Ming, Zhong
Abstract	In recent years, deep convolutional neural networks (CNN) have been widely used in computer vision and significantly improved the performance of image recognition tasks. Most works use softmax loss to supervise the training of CNN and then adopt the output of last layer as features. However, the discriminative capability of the softmax loss is limited. Here, the authors analyse and improve the softmax loss by manipulating the cosine value and input feature length. As the approach does not change the principle of the softmax loss, the network can easily be optimised by typical stochastic gradient descent. The MNIST handwritten digits dataset is employed to visualise the features learned by the improved softmax loss. The CASIA-WebFace and FER2013 training set are adopted to train deep CNN for face and expression recognition, respectively. Results on both the LFW dataset and FER2013 test set show that the proposed softmax loss can learn more discriminative features and achieve better performance.
Starting Page	97
Ending Page	102
Page Count	6
Volume Number	1
e-ISSN	25177567
Issue Number	Issue 4, Dec (2019)
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/ccs/1/4
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/10.1049/ccs.2019.0010
Journal	Cognitive Computation and Systems
Publisher	Shenzhen University The Institution of Engineering and Technology
Publisher Date	2019-09-30
Access Restriction	Open
Rights License	Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0/)
Subject Keyword	CASIA-WebFace Computer Vision Computer Vision And Image Processing Technique Convolutional Neural Nets Deep CNN Deep Convolutional Neural Network Deep Learning-based Face Recognition Discriminative Features Expression Recognition Face Recognition Feature Extraction FER2013 Training Set Gradient Method Image Recognition Improved Softmax Loss Interpolation And Function Approximation Knowledge Engineering Technique Learning in AI LFW Dataset MNIST Handwritten Digits Dataset Neural Computing Technique Numerical Analysis
Content Type	Text
Resource Type	Article

Central Library (ISO-9001:2015 Certified)
Indian Institute of Technology Kharagpur
Kharagpur, West Bengal, India | PIN - 721302

See location in the Map
03222 282435
Mail: support@ndl.gov.in

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in