Reinforced Wasserstein Training for Severity-Aware Semantic Segmentation in Autonomous Driving

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 improvements on the predefined important classes, and much longer continuous playtime in our simulator.

Accepted to IEEE Transactions on Intelligent Transportation Systems (T-ITS)

References in corpus (13)

• ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
• Deep Reinforcement Learning: An Overview
• Learning with a Wasserstein Loss
• CARLA: An Open Urban Driving Simulator
• Automated Evaluation of Semantic Segmentation Robustness for Autonomous Driving
• Latent Space Policies for Hierarchical Reinforcement Learning
• AUTO3D: Novel view synthesis through unsupervisely learned variational viewpoint and global 3D representation
• Permutation-invariant Feature Restructuring for Correlation-aware Image Set-based Recognition
• Conservative Wasserstein Training for Pose Estimation
• SAM: Squeeze-and-Mimic Networks for Conditional Visual Driving Policy Learning
• Learning to Navigate Using Mid-Level Visual Priors
• Learning by Cheating
• Importance-Aware Semantic Segmentation in Self-Driving with Discrete Wasserstein Training

Cited by in corpus (1)

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