Small Object Augmentation of Urban Scenes for Real-Time Semantic Segmentation
Lists
Only you see this
Abstract
Semantic segmentation is a key step in scene understanding for autonomous driving. Although deep learning has significantly improved the segmentation accuracy, current high-quality models such as PSPNet and DeepLabV3 are inefficient given their complex architectures and reliance on multi-scale inputs. Thus, it is difficult to apply them to real-time or practical applications. On the other hand, existing real-time methods cannot yet produce satisfactory results on small objects such as traffic lights, which are imperative to safe autonomous driving. In this paper, we improve the performance of real-time semantic segmentation from two perspectives, methodology and data. Specifically, we propose a real-time segmentation model coined Narrow Deep Network (NDNet) and build a synthetic dataset by inserting additional small objects into the training images. The proposed method achieves 65.7% mean intersection over union (mIoU) on the Cityscapes test set with only 8.4G floating-point operations (FLOPs) on <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$1024\times 2048$ </tex-math></inline-formula> inputs. Furthermore, by re-training the existing PSPNet and DeepLabV3 models on our synthetic dataset, we obtained an average 2% mIoU improvement on small objects.
BibTeX
@article{yang2020small,
author = {Zhengeng Yang and Hongshan Yu and Mingtao Feng and Wei Sun and Xuefei Lin and Mingui Sun and Zhi-Hong Mao and Ajmal Mian},
title = {{Small Object Augmentation of Urban Scenes for Real-Time Semantic Segmentation}},
journal = {IEEE Trans. Image Process.},
year = {2020},
url = {https://openreview.net/forum?id=WEdJEz2s4K},
}Loading related content...