Learning to Adapt Structured Output Space for Semantic Segmentation

CVPR 2018 Yi-Hsuan TsaiWei-Chih HungSamuel SchulterKihyuk SohnMing-Hsuan YangManmohan Chandraker

Convolutional neural network-based approaches for semantic segmentation rely on supervision with pixel-level ground truth, but may not generalize well to unseen image domains. As the labeling process is tedious and labor intensive, developing algorithms that can adapt source ground truth labels to the target domain is of great interest... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Synthetic-to-Real Translation GTAV-to-Cityscapes Labels Multi-level Adaptation mIoU 42.4 # 13
Synthetic-to-Real Translation GTAV-to-Cityscapes Labels Single-level Adaptation mIoU 41.4 # 14
Image-to-Image Translation SYNTHIA-to-Cityscapes Multi-level Adaptation mIoU 46.7 # 5
Image-to-Image Translation SYNTHIA-to-Cityscapes Single-level Adaptation mIoU 45.9 # 7