ThunderNet: A Turbo Unified Network for Real-Time Semantic Segmentation
Abstract
Recent research in pixel-wise semantic segmentation has increasingly focused on the development of very complicated deep neural networks, which require a large amount of computational resources. The ability to perform dense predictions in real-time, therefore, becomes tantamount to achieving high accuracies. This real-time demand turns out to be fundamental particularly on the mobile platform and other GPU-powered embedded systems like NVIDIA Jetson TX series. In this paper, we present a fast and efficient lightweight network called Turbo Unified Network (ThunderNet). With a minimum backbone truncated from ResNet18, ThunderNet unifies the pyramid pooling module with our customized decoder. Our experimental results show that ThunderNet can achieve 64.0% mIoU on CityScapes, with real-time performance of 96.2 fps on a Titan XP GPU (512x1024), and 20.9 fps on Jetson TX2 (256x512).
Cite
Text
Xiang et al. "ThunderNet: A Turbo Unified Network for Real-Time Semantic Segmentation." IEEE/CVF Winter Conference on Applications of Computer Vision, 2019. doi:10.1109/WACV.2019.00195Markdown
[Xiang et al. "ThunderNet: A Turbo Unified Network for Real-Time Semantic Segmentation." IEEE/CVF Winter Conference on Applications of Computer Vision, 2019.](https://mlanthology.org/wacv/2019/xiang2019wacv-thundernet/) doi:10.1109/WACV.2019.00195BibTeX
@inproceedings{xiang2019wacv-thundernet,
title = {{ThunderNet: A Turbo Unified Network for Real-Time Semantic Segmentation}},
author = {Xiang, Wei and Mao, Hongda and Athitsos, Vassilis},
booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
year = {2019},
pages = {1789-1796},
doi = {10.1109/WACV.2019.00195},
url = {https://mlanthology.org/wacv/2019/xiang2019wacv-thundernet/}
}