ICNet for Real-Time Semantic Segmentation on High-Resolution Images

ECCV 2018 Hengshuang ZhaoXiaojuan QiXiaoyong ShenJianping ShiJiaya Jia

We focus on the challenging task of real-time semantic segmentation in this paper. It finds many practical applications and yet is with fundamental difficulty of reducing a large portion of computation for pixel-wise label inference... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Real-Time Semantic Segmentation CamVid ICNet mIoU 67.1% # 3
Real-Time Semantic Segmentation CamVid ICNet Time (ms) 36 # 1
Real-Time Semantic Segmentation CamVid ICNet Frame (fps) 27.8 # 1
Real-Time Semantic Segmentation Cityscapes ICNet mIoU 70.6% # 5
Real-Time Semantic Segmentation Cityscapes ICNet Time (ms) 33 # 2
Real-Time Semantic Segmentation Cityscapes ICNet Frame (fps) 30.3 # 4
Semantic Segmentation Cityscapes ICNet Mean IoU 70.6% # 11