CRII: RI: Deep neural network pruning for fast and reliable visual detection in self-driving vehicles

该奖项全部或部分由2021年美国救援计划法案（公法117-2）资助。该项目的目标是简化大型通用深度神经网络，以实现自动驾驶车辆中快速可靠的视觉检测。该项目开发了紧凑的模型，需要更少的计算，能源消耗和二氧化碳排放。此外，这些紧凑型模型的较低延迟可以转化为紧急情况下更高的生存率。通过促进自动驾驶汽车的更广泛部署，该项目还将有助于降低与驾驶相关的劳动力成本，并为老年人和残疾人提供更大和更安全的流动性。最后，研究者将把项目的相关技术和发现介绍给课堂，并让来自不同背景的学生参与这项研究。这些活动将帮助学生们为美国汽车生产量最大的两个州--俄亥俄州和附近的密歇根州的未来汽车工业做好准备。这项研究通过深度网络修剪和对抗训练解决了高效可靠的自动驾驶视觉检测问题。核心假设是，在一个大型的通才网络中存在许多冗余的、与任务无关的、甚至是干扰性的参数/特征。当部署在自动驾驶车辆上时，这些不必要和过度装配的组件将使自动视觉检测变得缓慢，并为恶意攻击打开更多的大门。这类组成部分应予以削减或改进。该项目有两个具体目标：（1）创建一个用于自动驾驶视觉检测的深度网络修剪框架。该框架将是主动的（而不是在训练之后），并将利用位置和类别信息，以及（2）提高修剪后的自动驾驶检测器的鲁棒性。研究人员将研究修剪模型的对抗鲁棒性，并通过对抗训练寻求改进。这项研究可能会导致脱离为各种应用程序使用大型通用网络的主导趋势，以获得轻量级的专业网络，用于自动驾驶汽车中的高效和可靠的视觉检测。该项目将为完全（5级）自动驾驶提供一些技术。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

This award is funded in whole or in part under the American Rescue Plan Act of 2021 (Public Law 117-2).The objective of this project is to simplify large general-purpose deep neural networks for fast and trustworthy visual detection in self-driving vehicles. The project develops compact models that require less computation, energy consumption, and carbon dioxide emissions. In addition, lower latency of these compact models can translate to higher survival rates during emergencies. Through facilitating a wider deployment of self-driving cars, the project will also help reduce driving-related labor costs and provide greater and safe mobility to the elderly and the disabled. Finally, the investigator will introduce relevant technology and findings from the project to the classroom and involve students from diverse backgrounds in this research. These activities will prepare students for tomorrow's automobile industry in Ohio and nearby Michigan, the top two states for auto production in the US.This research addresses problems of efficient and reliable self-driving visual detection through deep network pruning and adversarial training. The central hypothesis is that there are many redundant, task-irrelevant, and even interfering parameters/features in a large generalist network. When deployed on self-driving vehicles, such unnecessary and overfitted components will render automated visual detection slow and open more doors for malign attacks. Such components should be pruned or improved. This project has two specific aims: (1) creating a deep network pruning framework for self-driving visual detection. The framework will be proactive (not after the fact of training) and will utilize both location and class information, and (2) improving the robustness of the pruned self-driving detectors. The investigator will study the adversarial robustness of the pruned models and seek improvement via adversarial training. The research can lead to departing from the dominant trend of employing large generalist networks for various applications to deriving lightweight specialist networks for efficient and reliable visual detection in self-driving cars. The project will provide some technologies towards fully (Level 5) autonomous driving.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.