No More Discrimination: Cross City Adaptation of Road Scene Segmenters

• Published in: Proceedings / IEEE International Conference on Computer Vision pp. 2011 - 2020
• Main Authors: Yi-Hsin Chen, Wei-Yu Chen, Yu-Ting Chen, Bo-Cheng Tsai, Wang, Yu-Chiang Frank, Min Sun
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.10.2017
• Subjects: Feature extraction; Google; Image segmentation; Roads; Semantics; Training; Urban areas

Despite the recent success of deep-learning based semantic segmentation, deploying a pre-trained road scene segmenter to a city whose images are not presented in the training set would not achieve satisfactory performance due to dataset biases. Instead of collecting a large number of annotated image...