Conditional Random Fields as Recurrent Neural Networks

ICCV 2015 Shuai ZhengSadeep JayasumanaBernardino Romera-ParedesVibhav VineetZhizhong SuDalong DuChang HuangPhilip H. S. Torr

Pixel-level labelling tasks, such as semantic segmentation, play a central role in image understanding. Recent approaches have attempted to harness the capabilities of deep learning techniques for image recognition to tackle pixel-level labelling tasks... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Semantic Segmentation Cityscapes CRF-RNN Mean IoU (class) 62.5% # 25
Real-Time Semantic Segmentation Cityscapes CRF-RNN mIoU 62.5% # 10
Real-Time Semantic Segmentation Cityscapes CRF-RNN Time (ms) 700 # 8
Real-Time Semantic Segmentation Cityscapes CRF-RNN Frame (fps) 1.4 # 10
Semantic Segmentation PASCAL Context CRF-RNN mIoU 39.3 # 14
Semantic Segmentation PASCAL VOC 2012 CRF-RNN Mean IoU 74.7% # 14