Safety Metrics for Semantic Segmentation in Autonomous Driving
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 18 of its 24 references that are in the map. First posted on arXiv 21 May 2021.
Builds on
18 of 24 references.
References · 18
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2013Intriguing properties of neural networkscited by 5,155
- 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
- 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
- 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
- 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,487
- 2016ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentationcited by 291
- 2017On the Robustness of Semantic Segmentation Models to Adversarial Attackscited by 126
6 more
- 2020Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentationcited by 38
- 2020Importance-Aware Semantic Segmentation in Self-Driving with Discrete Wasserstein Trainingcited by 27
- 2020Improved Noise and Attack Robustness for Semantic Segmentation by Using Multi-Task Training with Self-Supervised Depth Estimationcited by 26
- 2020A Safety Framework for Critical Systems Utilising Deep Neural Networkscited by 19
- 2020Towards the Quantification of Safety Risks in Deep Neural Networkscited by 4
- 2021A Framework for Assurance of Medication Safety using Machine Learningcited by 3
Built on by
Citing papers per year: 2022: 1; 2023: 1.
2 papers.