Dynamic Warping Network for Semantic Video Segmentation

Table 7

Comparison of state-of-the-art semantic video segmentation models on the CamVid test set.

Method	Source	mIoU %
STFCN [20]	arXiv2016	65.9
DFF [7]	CVPR2017	66.0
NetWarp [6]	ICCV2017	70.3
GRFP [15]	CVPR2018	66.1
Accel [8]	CVPR2019	69.3
EFC [13]	AAAI2020	67.4
TDNet [19]	CVPR2020	76.0
ESVS [17]	ECCV2020	76.3
PSPNet [33]	CVPR2017	75.4
PSPNet + ours		76.5

The bold values denote our method can achieve the best accuracy compared with other methods on the CamVid test set.