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

08/11/2020
by   Xiaofeng Liu, et al.
0

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.

READ FULL TEXT

page 1

page 3

page 7

page 8

research
10/21/2020

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

Semantic segmentation (SS) is an important perception manner for self-dr...
research
04/30/2021

Embedding Semantic Hierarchy in Discrete Optimal Transport for Risk Minimization

The widely-used cross-entropy (CE) loss-based deep networks achieved sig...
research
11/03/2019

Conservative Wasserstein Training for Pose Estimation

This paper targets the task with discrete and periodic class labels (e.g...
research
07/25/2019

Importance-Aware Semantic Segmentation with Efficient Pyramidal Context Network for Navigational Assistant Systems

Semantic Segmentation (SS) is a task to assign semantic label to each pi...
research
11/17/2016

Squared Earth Mover's Distance-based Loss for Training Deep Neural Networks

In the context of single-label classification, despite the huge success ...
research
07/19/2023

U-CE: Uncertainty-aware Cross-Entropy for Semantic Segmentation

Deep neural networks have shown exceptional performance in various tasks...
research
07/26/2022

Semantic Segmentation for Autonomous Driving: Model Evaluation, Dataset Generation, Perspective Comparison, and Real-Time Capability

Environmental perception is an important aspect within the field of auto...

Please sign up or login with your details

Forgot password? Click here to reset