erfnet

ERFNet

ERFNet: Efficient Residual Factorized ConvNet for Real-time Semantic Segmentation

Introduction

Official Repo

Code Snippet

Abstract

Semantic segmentation is a challenging task that addresses most of the perception needs of intelligent vehicles (IVs) in an unified way. Deep neural networks excel at this task, as they can be trained end-to-end to accurately classify multiple object categories in an image at pixel level. However, a good tradeoff between high quality and computational resources is yet not present in the state-of-the-art semantic segmentation approaches, limiting their application in real vehicles. In this paper, we propose a deep architecture that is able to run in real time while providing accurate semantic segmentation. The core of our architecture is a novel layer that uses residual connections and factorized convolutions in order to remain efficient while retaining remarkable accuracy. Our approach is able to run at over 83 FPS in a single Titan X, and 7 FPS in a Jetson TX1 (embedded device). A comprehensive set of experiments on the publicly available Cityscapes data set demonstrates that our system achieves an accuracy that is similar to the state of the art, while being orders of magnitude faster to compute than other architectures that achieve top precision. The resulting tradeoff makes our model an ideal approach for scene understanding in IV applications. The code is publicly available at: https://github.com/Eromera/erfnet.

Results and models

Cityscapes

Method	Backbone	Crop Size	Lr schd	Mem (GB)	Inf time (fps)	Device	mIoU	mIoU(ms+flip)	config	download
ERFNet	ERFNet	512x1024	160000	6.04	15.26	V100	72.5	74.75	config	model | log

Note:

• The model is trained from scratch.

• Last deconvolution layer in the original paper is replaced by a naive FCNHead decoder head and a bilinear upsampling layer, found more effective and efficient.

• This model performance is sensitive to the seed values used, please refer to the log file for the specific settings of the seed. If you choose a different seed, the results might differ from the table results.

Citation

@article{romera2017erfnet,
  title={Erfnet: Efficient residual factorized convnet for real-time semantic segmentation},
  author={Romera, Eduardo and Alvarez, Jos{\'e} M and Bergasa, Luis M and Arroyo, Roberto},
  journal={IEEE Transactions on Intelligent Transportation Systems},
  volume={19},
  number={1},
  pages={263--272},
  year={2017},
  publisher={IEEE}
}