ADFNet: accumulated decoder features for real-time semantic segmentation

Semantic segmentation is one of the important technologies in autonomous driving, and ensuring its real-time and high performance is of utmost importance for the safety of pedestrians and passengers. To improve its performance using deep neural networks that operate in real-time, the authors propose...

Full description

Saved in:
Bibliographic Details
Published in:IET computer vision 2020-12, Vol.14 (8), p.555-563
Main Authors: Choi, Hyunguk, Ahn, Hoyeon, Kim, Joonmo, Jeon, Moongu
Format: Article
Language:English
Subjects:
accumulated decoder features
ADFNet
autonomous driving
class activation maps
decoder information
deep neural networks
encoder
image colour analysis
image segmentation
neural nets
pedestrians
real‐time semantic segmentation
Research Article
RGB representations
Citations: Items that this one cites
Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Semantic segmentation is one of the important technologies in autonomous driving, and ensuring its real-time and high performance is of utmost importance for the safety of pedestrians and passengers. To improve its performance using deep neural networks that operate in real-time, the authors propose a simple and efficient method called ADFNet using accumulated decoder features, ADFNet operates by only using the decoder information without skip connections between the encoder and decoder. They demonstrate that the performance of ADFNet is superior to that of the state-of-the-art methods, including that of the baseline network on the cityscapes dataset. Further, they analyse the results obtained via ADFNet using class activation maps and RGB representations for image segmentation results.
ISSN:1751-9632
1751-9640
1751-9640
DOI:10.1049/iet-cvi.2019.0289