FOSNet: An End-to-End Trainable Deep Neural Network for Scene Recognition

Autor: Junhyuk Hyun, Euntai Kim, Hongje Seong
Rok vydání: 2020
Předmět:
FOS: Computer and information sciences
General Computer Science
Computer science
Computer Vision and Pattern Recognition (cs.CV)
Computer Science - Computer Vision and Pattern Recognition
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
convolutional neural network
Context (language use)
02 engineering and technology
01 natural sciences
Convolutional neural network
Image (mathematics)
scene coherence
End-to-end principle
0103 physical sciences
0202 electrical engineering
electronic engineering
information engineering
General Materials Science
Computer vision
010306 general physics
ComputingMethodologies_COMPUTERGRAPHICS
Artificial neural network
business.industry
General Engineering
fusion network
Object (computer science)
Class (biology)
Scene recognition
end-to-end trainable
020201 artificial intelligence & image processing
lcsh:Electrical engineering. Electronics. Nuclear engineering
Artificial intelligence
business
lcsh:TK1-9971
Coherence (physics)
Zdroj: IEEE Access, Vol 8, Pp 82066-82077 (2020)
ISSN: 2169-3536
DOI: 10.1109/access.2020.2989863
Popis: Scene recognition is an image recognition problem aimed at predicting the category of the place at which the image is taken. In this paper, a new scene recognition method using the convolutional neural network (CNN) is proposed. The proposed method is based on the fusion of the object and the scene information in the given image and the CNN framework is named as FOS (fusion of object and scene) Net. In addition, a new loss named scene coherence loss (SCL) is developed to train the FOSNet and to improve the scene recognition performance. The proposed SCL is based on the unique traits of the scene that the 'sceneness' spreads and the scene class does not change all over the image. The proposed FOSNet was experimented with three most popular scene recognition datasets, and their state-of-the-art performance is obtained in two sets: 60.14% on Places 2 and 90.37% on MIT indoor 67. The second highest performance of 77.28% is obtained on SUN 397.
Comment: 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
Databáze: OpenAIRE
Externí odkaz: