Cross-Domain Complementary Learning Using Pose for Multi-Person Part Segmentation

11 Jul 2019Kevin LinLijuan WangKun LuoYinpeng ChenZicheng LiuMing-Ting Sun

Supervised deep learning with pixel-wise training labels has great successes on multi-person part segmentation. However, data labeling at pixel-level is very expensive... (read more)

PDF Abstract

Results from the Paper


 SOTA for Human Part Segmentation on PASCAL-Person-Part (using extra training data)

     Get a GitHub badge
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
RESULT LEADERBOARD
Human Part Segmentation PASCAL-Person-Part CDCL mIoU 65.02 # 5
Human Part Segmentation PASCAL-Person-Part CDCL+Pascal mIoU 72.82 # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet