Wasserstein loss with alternative reinforcement learning for severity-aware semantic segmentation

Xiaofeng Liu, Yunhong Lu, Xiongchang Liu, Song Bai, Site Li, Jia You

Research output: Journal article publicationJournal articleAcademic researchpeer-review

3 Citations (Scopus)

Abstract

Semantic segmentation is important for many real-world systems, e.g., autonomous vehicles, which predict the class of each pixel. Recently, deep networks achieved significant progress w.r.t. the mean Intersection-over Union (mIoU) with the cross-entropy loss. However, the cross entropy loss can essentially ignore the difference of severity for an autonomous car with different wrong prediction mistakes. For example, predicting the car to the road is much more servery than recognize it as the bus. Targeting for this difficulty, we develop a Wasserstein training framework to explore the inter-class correlation by defining its ground metric as misclassification severity. The ground metric of Wasserstein distance can be pre-defined following the experience on a specific task. From the optimization perspective, we further propose to set the ground metric as an increasing function of the pre-defined ground metric. Furthermore, an adaptively learning scheme of the ground matrix is proposed to utilize the high-fidelity CARLA simulator. Specifically, we follow a reinforcement alternative learning scheme. The experiments on both CamVid and Cityscapes datasets evidenced the effectiveness of our Wasserstein loss. The SegNet, ENet, FCN and Deeplab networks can be adapted following a plug in manner. We achieve significant improves on the predefined important classes, and much longer continuous play time in our simulator.
Original languageEnglish
Pages (from-to)587 - 596
Number of pages10
JournalIEEE Transactions on Intelligent Transportation Systems
Volume23
Issue number1
DOIs
Publication statusPublished - 1 Jan 2022

Keywords

  • Semantic segmentation
  • Wasserstein training
  • actor-critic
  • autonomous driving

ASJC Scopus subject areas

  • Automotive Engineering
  • Mechanical Engineering
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Wasserstein loss with alternative reinforcement learning for severity-aware semantic segmentation'. Together they form a unique fingerprint.

Cite this