Context Prior for Scene Segmentation

3 Apr 2020Changqian YuJingbo WangChangxin GaoGang YuChunhua ShenNong Sang

Recent works have widely explored the contextual dependencies to achieve more accurate segmentation results. However, most approaches rarely distinguish different types of contextual dependencies, which may pollute the scene understanding... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Semantic Segmentation ADE20K CPN(ResNet-101) Validation mIoU 46.27 # 4
Semantic Segmentation ADE20K val CPN(ResNet-101) mIoU 46.27% # 5
Scene Understanding ADE20K val CPN(ResNet-101) Mean IoU 46.3 # 1
Semantic Segmentation Cityscapes test CPN(ResNet-101) Mean IoU (class) 81.3% # 21
Semantic Segmentation PASCAL Context CPN(ResNet-101) mIoU 53.9 # 8