TY - GEN
T1 - RailSAM
T2 - 28th International Conference on Intelligent Transportation Systems, ITSC 2025
AU - Zhang, Wenze
AU - Lin, Chunmian
AU - Tian, Daxin
AU - Duan, Xuting
AU - Zhou, Jianshan
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025
Y1 - 2025
N2 - The emergence of vision foundation model, such as the Segment Anything Model (SAM), has brought groundbreaking advancements to downstream tasks due to its zero-shot transfer capability. In this work, RailSAM is proposed by incorporating the SAM generalist architecture with domain-specific adapter for railway segmentation. By leveraging the pretrained knowledge from the frozen SAM encoder, we seamlessly inject domain-specific information through visual prompts into the mask decoder via carefully designed adapters. On the publicly available RailSem19 dataset, our experiments demonstrate that RailSAM significantly outperforms existing task-specific methods and exhibits remarkable robustness under challenging conditions. We hope this work would inspire in-depth exploration of vision foundation model for intelligent railway transportation. The code will be open-source soon.
AB - The emergence of vision foundation model, such as the Segment Anything Model (SAM), has brought groundbreaking advancements to downstream tasks due to its zero-shot transfer capability. In this work, RailSAM is proposed by incorporating the SAM generalist architecture with domain-specific adapter for railway segmentation. By leveraging the pretrained knowledge from the frozen SAM encoder, we seamlessly inject domain-specific information through visual prompts into the mask decoder via carefully designed adapters. On the publicly available RailSem19 dataset, our experiments demonstrate that RailSAM significantly outperforms existing task-specific methods and exhibits remarkable robustness under challenging conditions. We hope this work would inspire in-depth exploration of vision foundation model for intelligent railway transportation. The code will be open-source soon.
KW - Intelligent Transportation Systems
KW - Parameter-efficient Fine-tuning
KW - Railway Segmentation
KW - Segment Anything Model
UR - https://www.scopus.com/pages/publications/105036955371
U2 - 10.1109/ITSC60802.2025.11423044
DO - 10.1109/ITSC60802.2025.11423044
M3 - 会议稿件
AN - SCOPUS:105036955371
T3 - IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC
SP - 3923
EP - 3929
BT - IEEE Intelligent Transportation Systems Conference, ITSC 2025
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 18 November 2025 through 21 November 2025
ER -