Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes

ICCV 2017 Yang ZhangPhilip DavidBoqing Gong

During the last half decade, convolutional neural networks (CNNs) have triumphed over semantic segmentation, which is one of the core tasks in many applications such as autonomous driving. However, to train CNNs requires a considerable amount of data, which is difficult to collect and laborious to annotate... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Synthetic-to-Real Translation GTAV-to-Cityscapes Labels CDA mIoU 28.9 # 23
Image-to-Image Translation SYNTHIA-to-Cityscapes CDA mIoU 29.0 # 13