Effective Source-Aware Domain Enhancement and Adaptation for CNN-Based Object Segmentation

Effective Source-Aware Domain Enhancement and Adaptation for CNN-Based Object Segmentation

In this paper, we propose an effective source-aware domain enhancement and adaptation (SDEA) approach to increase the accuracy of the existing convolutional neural network-based (CNN-based) object segmentation methods. We first scoop out the source elements, such as the falling-leaves, manhole cover...

Full description

Bibliographic Details
Main Authors: Kuo-Liang Chung, Ya-Yun Cheng
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Automatic driving assistance systems (ADAS)
convolutional neural networks (CNN)
domain adaptation
domain enhancement
Grand Theft Auto V (GTA5)
mean intersection over union (mIoU)
Online Access:https://ieeexplore.ieee.org/document/9166480/

Internet

https://ieeexplore.ieee.org/document/9166480/

Similar Items