AutoJoin: Efficient Adversarial Training for Robust Maneuvering via Denoising Autoencoder and Joint Learning

CoRR(2022)

引用 0|浏览9
暂无评分
摘要
As a result of increasingly adopted machine learning algorithms and ubiquitous sensors, many 'perception-to-control' systems are developed and deployed. For these systems to be trustworthy, we need to improve their robustness with adversarial training being one approach. We propose a gradient-free adversarial training technique, called AutoJoin, which is a very simple yet effective and efficient approach to produce robust models for imaged-based maneuvering. Compared to other SOTA methods with testing on over 5M perturbed and clean images, AutoJoin achieves significant performance increases up to the 40% range under gradient-free perturbations while improving on clean performance up to 300%. Regarding efficiency, AutoJoin demonstrates strong advantages over other SOTA techniques by saving up to 83% time per training epoch and 90% training data. Although not the focus of AutoJoin, it even demonstrates superb ability in defending gradient-based attacks. The core idea of AutoJoin is to use a decoder attachment to the original regression model creating a denoising autoencoder within the architecture. This architecture allows the tasks 'maneuvering' and 'denoising sensor input' to be jointly learnt and reinforce each other's performance.
更多
查看译文
关键词
autonomous driving,machine learning,robust training
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要