arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.16952cs.CVcs.AI
收藏

面向自动驾驶的瞬态容错语义分割

Transient Fault Tolerant Semantic Segmentation for Autonomous Driving

Politecnico di Torino(都灵理工大学);Univ Rennes(雷恩大学);INRIA(法国国家信息与自动化研究所);Università di Trento(特伦托大学)

Leonardo Iurada, Niccolò Cavagnero, Fernando Fernandes Dos Santos, Giuseppe Averta, Paolo Rech, Tatiana Tommasi

AI总结:

针对自动驾驶语义分割模型的硬件瞬态故障问题,提出一种新型激活函数ReLUMax,在不增加时间开销的前提下提升模型容错鲁棒性与预测置信度。

摘要:

深度学习模型对于自动驾驶车辆感知至关重要,但其可靠性受到算法局限性和硬件故障的挑战。我们通过考察语义分割模型中的容错性来解决后者。利用已有的硬件故障模型,我们从准确性和不确定性两方面评估了现有的加固技术,并引入了ReLUMax,这是一种新颖且简单的激活函数,旨在增强对瞬态故障的鲁棒性。ReLUMax能够无缝集成到现有架构中,且不带来时间开销。我们的实验表明,ReLUMax有效提升了鲁棒性,在保持性能的同时增强了预测置信度,从而为开发可靠的自动驾驶系统做出了贡献。

英文摘要:

Deep learning models are crucial for autonomous vehicle perception, but their reliability is challenged by algorithmic limitations and hardware faults. We address the latter by examining fault-tolerance in semantic segmentation models. Using established hardware fault models, we evaluate existing hardening techniques both in terms of accuracy and uncertainty and introduce ReLUMax, a novel simple activation function designed to enhance resilience against transient faults. ReLUMax integrates seamlessly into existing architectures without time overhead. Our experiments demonstrate that ReLUMax effectively improves robustness, preserving performance and boosting prediction confidence, thus contributing to the development of reliable autonomous driving systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑