Dual-Stream Adapters for Open-Set Segmentation in Driving Scenes


Shyam Nandan Rai (Politecnico di Torino), Massimiliano Mancini (University of Trento), Barbara Caputo (Politecnico di Torino), Carlo Masone (Politecnico di Torino)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)Supplementary

Abstract

The task of segmenting novel categories in road scenes, often referred to as anomaly segmentation, has been recently addressed with great success by using mask-based architectures, but their efficacy is dependent on fine-tuning large transformer backbones. In this work, we design a specialized adapter for this task, which makes it possible to leverage even large backbones without re-training them. The key feature of our adapter is the separation of the adapted features in two streams, one specialized on the known categories (in-distribution) and the other that captures the characteristics of out-of-distribution categories. The out-of-distribution features adaptation is supervised by using synthetic negative data generated by a normalizing flow process. This dual-stream architecture allows to better disentangle features for known and unknown categories, preserving in-distribution performance while enabling direct and more accurate anomaly segmentation with fewer false positives. Experiments show that dual-stream adapters outperform previous methods while reducing training parameters by 38\%.

Citation

@inproceedings{Rai_2025_BMVC,
author    = {Shyam Nandan Rai and Massimiliano Mancini and Barbara Caputo and Carlo Masone},
title     = {Dual-Stream Adapters for Open-Set Segmentation in Driving Scenes},
booktitle = {36th British Machine Vision Conference 2025, {BMVC} 2025, Sheffield, UK, November 24-27, 2025},
publisher = {BMVA},
year      = {2025},
url       = {https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_603/paper.pdf}
}


Copyright © 2025 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection