Gradient-Free Adversarial Training Against Image Corruption for Learning-based Steering

We introduce a simple yet effective framework for improving the robustness of learning algorithms against image corruptions for autonomous driving. These corruptions can occur due to both internal (e. g. , sensor noises and hardware abnormalities) and external factors (e. g. , lighting, weather, visibility, and other environmental effects). Using sensitivity analysis with FID-based parameterization, we propose a novel algorithm exploiting basis perturbations to improve the overall performance of autonomous steering and other image processing tasks, such as classification and detection, for self-driving cars. Our model not only improves the performance on the original dataset, but also achieves significant performance improvement on datasets with multiple and unseen perturbations, up to 87% and 77%, respectively. A comparison between our approach and other SOTA techniques confirms the effectiveness of our technique in improving the robustness of neural network training for learning-based steering and other image processing tasks.

Authors

• Yu Shen Key Lab of High Confidence Software Technologies, Peking University, China Kuaishou Technology, China
• Laura Zheng
• Manli Shu
• Weizi Li
• Tom Goldstein University of Maryland, College Park
• Ming Lin Independent Researcher

Keywords

No keywords are indexed for this paper.