.png){kind=icon}
返回
NDNet: Narrow While Deep Network for Real-Time Semantic Segmentation
.png){kind=icon}
OA
AI
DOI：10.1109/TITS.2020.2987816.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The rapid development of autonomous driving in recent years presents many challenges for scene understanding. As an essential step towards scene understanding, semantic segmentation has received increased attention in the past few years. Although deep learning based approaches have achieved great success in improving the segmentation accuracy, most of them suffer from an inefficiency problem and can hardly be applied to real-time applications. In this paper, we analyze the computational cost of Convolutional Neural Network (CNN) and find that the inefficiency of CNNs is mainly caused by their wide structure rather than deep structure. In addition, the success of pruning based model compression methods proves that there are many redundant channels in CNNs. Thus, we design a narrow while deep backbone network to improve the efficiency of semantic segmentation. By casting our network to fully convolutional network (FCN32) segmentation architecture, the basic structure of most segmentation methods, we achieve 61.5% mIoU on Cityscapes validation dataset with only 4.2G floating-point operations (FLOPs) on 1024 x 2048 inputs, which already outperforms one of the earliest real-time deep learning based segmentation methods: ENet (58.3% mIoU, 3.8G FLOPs on 640x360 inputs). By further refining the output resolution of our network to the 1/8 of the input resolution with a simple encoder-decoder structure, we achieve 65.3% mIoU on Cityscapes test set with 14.0G FLOPs and 39.9 frames per second (FPS) on Titan X card. We have made our model publicly available at https://github.com/zgyang-hnu/NDNet.
Keyword:
Semantic segmentation
autonomous driving
real-time
deep learning
期刊
IF:
8.4
论文数:
9.7K
被引数:
6.3W
机构
引用论文
Mist Control at a Machining Center, Part 2: Mist Control Following Installation of Air Cleaners
PREAI
分享收藏Distant regulatory elements in a Sox10‐βGEO BAC transgene are required for expression of Sox10 in the enteric nervous system and other neural crest‐derived tissuesSox10-βgeo BAC转基因中的远距离调控元件是肠神经系统和其他神经源性组织中 Sox10 表达所必需的
OAAI
OAAI分享收藏Locally Shared Features: An Efficient Alternative to Conditional Random Field for Semantic Segmentation.png)
IEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏
查看更多内容