DeepAI AI Chat
Log In Sign Up

Safety Metrics for Semantic Segmentation in Autonomous Driving

by   Chih-Hong Cheng, et al.

Within the context of autonomous driving, safety-related metrics for deep neural networks have been widely studied for image classification and object detection. In this paper, we further consider safety-aware correctness and robustness metrics specialized for semantic segmentation. The novelty of our proposal is to move beyond pixel-level metrics: Given two images with each having N pixels being class-flipped, the designed metrics should, depending on the clustering of pixels being class-flipped or the location of occurrence, reflect a different level of safety criticality. The result evaluated on an autonomous driving dataset demonstrates the validity and practicality of our proposed methodology.


Efficacy of Pixel-Level OOD Detection for Semantic Segmentation

The detection of out of distribution samples for image classification ha...

Learning Uncertainty For Safety-Oriented Semantic Segmentation In Autonomous Driving

In this paper, we show how uncertainty estimation can be leveraged to en...

Safety Metrics and Losses for Object Detection in Autonomous Driving

State-of-the-art object detectors have been shown effective in many appl...

Plants Don't Walk on the Street: Common-Sense Reasoning for Reliable Semantic Segmentation

Data-driven sensor interpretation in autonomous driving can lead to high...

SoildNet: Soiling Degradation Detection in Autonomous Driving

In the field of autonomous driving, camera sensors are extremely prone t...

Street-Map Based Validation of Semantic Segmentation in Autonomous Driving

Artificial intelligence for autonomous driving must meet strict requirem...

Automated Evaluation of Semantic Segmentation Robustness for Autonomous Driving

One of the fundamental challenges in the design of perception systems fo...