Skip to main navigation Skip to search Skip to main content

RailSAM: Taming SAM with Adapter for Railway Segmentation

  • Beihang University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

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.

Original languageEnglish
Title of host publicationIEEE Intelligent Transportation Systems Conference, ITSC 2025
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3923-3929
Number of pages7
ISBN (Electronic)9798331524180
DOIs
StatePublished - 2025
Event28th International Conference on Intelligent Transportation Systems, ITSC 2025 - Gold Coast, Australia
Duration: 18 Nov 202521 Nov 2025

Publication series

NameIEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC
ISSN (Print)2153-0009
ISSN (Electronic)2153-0017

Conference

Conference28th International Conference on Intelligent Transportation Systems, ITSC 2025
Country/TerritoryAustralia
CityGold Coast
Period18/11/2521/11/25

Keywords

  • Intelligent Transportation Systems
  • Parameter-efficient Fine-tuning
  • Railway Segmentation
  • Segment Anything Model

Fingerprint

Dive into the research topics of 'RailSAM: Taming SAM with Adapter for Railway Segmentation'. Together they form a unique fingerprint.

Cite this