P_VggNet: A convolutional neural network (CNN) with pixel-based attention map

Autor: Kaige Yang, Yi Zheng, Kunhua Liu, Liu Mei, Peisi Zhong
Rok vydání: 2018
Předmět:
Computer science
Social Sciences
02 engineering and technology
Facial recognition system
Convolutional neural network
Pattern Recognition
Automated
Grayscale
Machine Learning
Cognition
Learning and Memory
Medicine and Health Sciences
Image Processing
Computer-Assisted
0202 electrical engineering
electronic engineering
information engineering
Psychology
Attention
Multidisciplinary
Artificial neural network
Experimental Design
Net (mathematics)
Research Design
Feature (computer vision)
Pattern recognition (psychology)
Medicine
Engineering and Technology
020201 artificial intelligence & image processing
Anatomy
Algorithms
Research Article
Computer and Information Sciences
Neural Networks
Science
Equipment
Image processing
Digital Imaging
Research and Analysis Methods
Face Recognition
Memory
Artificial Intelligence
Support Vector Machines
Humans
business.industry
Cognitive Psychology
Biology and Life Sciences
020206 networking & telecommunications
Pattern recognition
Image Enhancement
Support vector machine
Face
Cognitive Science
Perception
Neural Networks
Computer
Artificial intelligence
business
Head
Neuroscience
Zdroj: PLoS ONE
PLoS ONE, Vol 13, Iss 12, p e0208497 (2018)
ISSN: 1932-6203
DOI: 10.1371/journal.pone.0208497
Popis: Attention maps have been fused in the VggNet structure (EAC-Net) [1] and have shown significant improvement compared to that of the VggNet structure. However, in [1], E-Net was designed based on the facial action unit (AU) center and for facial AU detection only. Thus, for the use of attention maps in every image type, this paper proposed a new convolutional neural network (CNN) structure, P_VggNet, comprising the following parts: P_Net and VggNet with 16 layers (VggNet-16). The generation approach of P_Net was designed, and the P_VggNet structure was proposed. To prove the efficiency of P_VggNet, we designed two experiments, which indicated that P_VggNet could more efficiently extract image features than VggNet-16.
Databáze: OpenAIRE
Externí odkaz: