Scholarlink

<p>This paper addresses perception degradation caused by adverse weather, occlusion, and asynchronous sampling by proposing an uncertainty-weighted multi-task learning framework for robust semantic understanding of traffic scenes (UW-MTL). The method performs differentiable multi-source spatiotemporal alignment to unify camera, LiDAR, radar, and IMU into a BEV sequence, and adopts a hybrid backbone that combines a Mixture of Experts Transformer with a spatiotemporal graph neural network to balance global semantics and local topology. Each task employs evidential prediction heads that explicitly output confidence and uncertainty. During training, soft-temperature weighting and a sigma aware gradient conflict resolver enable stable joint optimization. On the nuScenes benchmark, UW-MTL consistently surpasses BEVFusion and UniAD on 3D object detection, BEV semantic segmentation, and short-horizon trajectory prediction, with especially pronounced gains at long range, under heavy occlusion, and in low-visibility conditions.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Uncertainty weighted multi task learning for robust traffic scene semantic understanding

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月20日

查看全文
  • Zhiping Wan,
  • Shitong Ye,
  • Feng Wang,
  • Shaojiang Liu,
  • Ling Peng

摘要

This paper addresses perception degradation caused by adverse weather, occlusion, and asynchronous sampling by proposing an uncertainty-weighted multi-task learning framework for robust semantic understanding of traffic scenes (UW-MTL). The method performs differentiable multi-source spatiotemporal alignment to unify camera, LiDAR, radar, and IMU into a BEV sequence, and adopts a hybrid backbone that combines a Mixture of Experts Transformer with a spatiotemporal graph neural network to balance global semantics and local topology. Each task employs evidential prediction heads that explicitly output confidence and uncertainty. During training, soft-temperature weighting and a sigma aware gradient conflict resolver enable stable joint optimization. On the nuScenes benchmark, UW-MTL consistently surpasses BEVFusion and UniAD on 3D object detection, BEV semantic segmentation, and short-horizon trajectory prediction, with especially pronounced gains at long range, under heavy occlusion, and in low-visibility conditions.