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 test CRF-RNN Mean IoU (class) 62.5% # 47
Real-Time Semantic Segmentation Cityscapes test CRF-RNN mIoU 62.5% # 12
Real-Time Semantic Segmentation Cityscapes test CRF-RNN Time (ms) 700 # 9
Real-Time Semantic Segmentation Cityscapes test CRF-RNN Frame (fps) 1.4 # 11
Semantic Segmentation PASCAL Context CRF-RNN mIoU 39.3 # 20
Semantic Segmentation PASCAL VOC 2012 test CRF-RNN Mean IoU 74.7% # 21