EASeg: Environmental adaptation for weakly-supervised autonomous driving semantic segmentation

• Published in: Information processing & management Vol. 63; no. 1; p. 104349
• Main Authors: Li, Yongqiang, Hu, Chuanping, Ren, Kai, Xi, Hao, Fan, Jinhao
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.01.2026
• Subjects: Autonomous driving; Boundary refinement; Environmental adaptation; Feature reliability; Weakly supervised semantic segmentation; Environmental adaptation; Feature reliability; Weakly supervised semantic segmentation; Autonomous driving; Boundary refinement

Weakly supervised semantic segmentation (WSSS) offers a promising solution to reduce annotation costs in autonomous driving perception systems. However, existing methods struggle with the complex environmental conditions inherent to real-world driving scenarios, including adverse weather, variable l...