Importance-Aware Semantic Segmentation in Self-Driving with Discrete Wasserstein Training


  • Xiaofeng Liu Harvard University
  • Yuzhuo Han Dalian University of Technology
  • Song Bai UC Berkeley
  • Yi Ge Carnegie Mellon University
  • Tianxing Wang Fudan University
  • Xu Han Johns Hopkins University
  • Site Li Carnegie Mellon University
  • Jane You The Hong Kong Polytechnic University
  • Jun Lu Harvard Medical School



Semantic segmentation (SS) is an important perception manner for self-driving cars and robotics, which classifies each pixel into a pre-determined class. The widely-used cross entropy (CE) loss-based deep networks has achieved significant progress w.r.t. the mean Intersection-over Union (mIoU). However, the cross entropy loss can not take the different importance of each class in an self-driving system into account. For example, pedestrians in the image should be much more important than the surrounding buildings when make a decisions in the driving, so their segmentation results are expected to be as accurate as possible. In this paper, we propose to incorporate the importance-aware inter-class correlation in a Wasserstein training framework by configuring its ground distance matrix. The ground distance matrix can be pre-defined following a priori in a specific task, and the previous importance-ignored methods can be the particular cases. From an optimization perspective, we also extend our ground metric to a linear, convex or concave increasing function w.r.t. pre-defined ground distance. We evaluate our method on CamVid and Cityscapes datasets with different backbones (SegNet, ENet, FCN and Deeplab) in a plug and play fashion. In our extenssive experiments, Wasserstein loss demonstrates superior segmentation performance on the predefined critical classes for safe-driving.




How to Cite

Liu, X., Han, Y., Bai, S., Ge, Y., Wang, T., Han, X., Li, S., You, J., & Lu, J. (2020). Importance-Aware Semantic Segmentation in Self-Driving with Discrete Wasserstein Training. Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 11629-11636.



AAAI Technical Track: Vision