Paper Info
Title
Research on Multitask Deep Learning Network for Semantic Segmentation and Object Detection.
Abstract
After analyzing methods of object detection under the existing deep learning framework, a multitask learning model (Fully Convolution Object Detection Network, FCDN) is proposed, which can realize complete end to end semantic segmentation and object detection through deep learning, without delimiting the default boxes. First, this paper analysis the reason why the current mainstream object detection network needs the default box delineated in advance; second, an object detection network with no delimited default box needed is proposed. It uses the semantic segmentation to detect all boundaries and key points of object at the pixel level, and then obtain prediction boxes by combining the category information of the semantic segmentation map. Finally, the feasibility of the method is verified on the VOC 2007 datasets, and compared with the performance of current mainstream object detection algorithm. Results show that the semantic segmentation and object detection can be realized at the same time by the new model. Trained by the same training sample, detection precision of FCDN is superior to that of classic detection models.
Year
DOI
Venue
2018
10.1007/978-3-030-00764-5_65
ADVANCES IN MULTIMEDIA INFORMATION PROCESSING, PT III
Keywords
Field
DocType
Deep learning,Object detection,Semantic segmentation,Object boundary key points,Default boxes
Computer vision,Object detection,Multi-task learning,Pattern recognition,Convolution,Computer science,End-to-end principle,Segmentation,Pixel,Artificial intelligence,Deep learning
Conference
Volume
ISSN
Citations 
11166
0302-9743
0
PageRank 
References 
Authors
0.34
15
6
Name
Order
Citations
PageRank
Ting Rui14712.22
Feng Xiao2197.22
Jian Tang311.72
Fukai Zhang400.68
Chengsong Yang543.46
Min Liu65616.44