.png){kind=icon}
返回
Adversarial Differentiable Data Augmentation for Autonomous Systems
.png){kind=icon}
PRE
AI
DOI：10.1109/ICRA48506.2021.9561205.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Autonomous systems often rely on neural networks to achieve high performance on planning and control problems. Unfortunately, neural networks suffer severely when input images become degraded in ways that are not reflected in the training data. This is particularly problematic for robotic systems like autonomous vehicles (AV) for which reliability is paramount. In this work, we consider robust optimization methods for hardening control systems against image corruptions and other unexpected domain shifts. Recent work on robust optimization for neural nets has been focused largely on combating adversarial attacks. In this work, we borrow ideas from the adversarial training and data augmentation literature to enhance robustness to image corruptions and domain shifts. To this end, we train networks while augmenting image data with a battery of image degradations. Unlike traditional augmentation methods, we choose the parameters for each degradation adversarially so as to maximize system performance. By formulating image degradations in a way that is differentiable with respect to degradation parameters, we enable the use of efficient optimization methods (PGD) for choosing worst-case augmentation parameters. We demonstrate the efficacy of this method on the learning to steer task for AVs. By adversarially training against image corruptions, we produce networks that are highly robust to image corruptions. We show that the proposed differentiable augmentation schemes result in higher levels of robustness and accuracy for a range of settings as compared to baseline and state-of-the-art augmentation methods.
期刊
I
IF:
0
论文数:
33
被引数:
0
机构
引用论文
分享收藏Restored Circulating Invariant NKT Cells Are Associated with Viral Control in Patients with Chronic Hepatitis B.png)
PLoS ONE
OAAI
PLoS ONEIF0
OAAI分享收藏Interferon alpha treatment stimulates interferon gamma expression in type I NKT cells and enhances their antiviral effect against hepatitis C virusPLOS ONEOAAI
PLOS ONEIF0
OAAI分享收藏
查看更多内容