TGV Upsampling: A Making-Up Operation for Semantic Segmentation
Joint Authors
Shin, Byeong-Seok
Yin, Xu
Li, Yan
Source
Computational Intelligence and Neuroscience
Issue
Vol. 2019, Issue 2019 (31 Dec. 2019), pp.1-12, 12 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2019-08-01
Country of Publication
Egypt
No. of Pages
12
Main Subjects
Abstract EN
With the widespread use of deep learning methods, semantic segmentation has achieved great improvements in recent years.
However, many researchers have pointed out that with multiple uses of convolution and pooling operations, great information loss would occur in the extraction processes.
To solve this problem, various operations or network architectures have been suggested to make up for the loss of information.
We observed a trend in many studies to design a network as a symmetric type, with both parts representing the “encoding” and “decoding” stages.
By “upsampling” operations in the “decoding” stage, feature maps are constructed in a certain way that would more or less make up for the losses in previous layers.
In this paper, we focus on upsampling operations, make a detailed analysis, and compare current methods used in several famous neural networks.
We also combine the knowledge on image restoration and design a new upsampled layer (or operation) named the TGV upsampling algorithm.
We successfully replaced upsampling layers in the previous research with our new method.
We found that our model can better preserve detailed textures and edges of feature maps and can, on average, achieve 1.4–2.3% improved accuracy compared to the original models.
American Psychological Association (APA)
Yin, Xu& Li, Yan& Shin, Byeong-Seok. 2019. TGV Upsampling: A Making-Up Operation for Semantic Segmentation. Computational Intelligence and Neuroscience،Vol. 2019, no. 2019, pp.1-12.
https://search.emarefa.net/detail/BIM-1129627
Modern Language Association (MLA)
Yin, Xu…[et al.]. TGV Upsampling: A Making-Up Operation for Semantic Segmentation. Computational Intelligence and Neuroscience No. 2019 (2019), pp.1-12.
https://search.emarefa.net/detail/BIM-1129627
American Medical Association (AMA)
Yin, Xu& Li, Yan& Shin, Byeong-Seok. TGV Upsampling: A Making-Up Operation for Semantic Segmentation. Computational Intelligence and Neuroscience. 2019. Vol. 2019, no. 2019, pp.1-12.
https://search.emarefa.net/detail/BIM-1129627
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1129627