English(EN) Closed Loop Dynamic Driving Data Mixture for Real-Synthetic Co-Training

新的AutoScale引擎优化用于驾驶模型的真实-合成数据

作者 PulseAugur 编辑部 · [2 个来源] · 2026-05-20 16:36

研究人员开发了AutoScale，一种新颖的闭环数据引擎，旨在优化用于训练自动驾驶模型的真实和合成数据的混合。该系统根据性能反馈动态调整数据组成，解决了分布变化和数据利用效率低下等挑战。AutoScale利用图正则自编码器进行场景表示，并利用聚类感知梯度上升进行样本重加权，在实验中证明了使用更少合成样本即可获得改进的性能。 AI

影响这项研究通过优化数据混合，可能导致更高效的自动驾驶系统训练。

排序理由该集群包含一篇详细介绍AI研究新方法和系统的学术论文。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.AI TIER_1 English(EN) · Hongzhi Ruan, Pei Liu, Weiliang Ma, Zhengning Li, Xueyang Zhang, Jun Ma, Dan Xu, Kun Zhan · 2026-05-22 04:00

Closed Loop Dynamic Driving Data Mixture for Real-Synthetic Co-Training

arXiv:2605.21372v1 Announce Type: cross Abstract: Data scaling is fundamental to modern deep learning, and grows increasingly critical as autonomous driving shifts to end-to-end learning. Real-world driving data is expensive to annotate and scene-biased, making real-synthetic co-…
arXiv cs.AI TIER_1 English(EN) · Kun Zhan · 2026-05-20 16:36

Closed Loop Dynamic Driving Data Mixture for Real-Synthetic Co-Training

Data scaling is fundamental to modern deep learning, and grows increasingly critical as autonomous driving shifts to end-to-end learning. Real-world driving data is expensive to annotate and scene-biased, making real-synthetic co-training with near-infinite synthetic data a promi…

报道来源 [2]

Closed Loop Dynamic Driving Data Mixture for Real-Synthetic Co-Training

Closed Loop Dynamic Driving Data Mixture for Real-Synthetic Co-Training

相关话题