WeatherSeg: Weather-Robust Image Segmentation using Teacher-Student Dual Learning and Classifier-Updating Attention

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Zhang, Zeng, Yifeng, Jiang, Houshi, Pan, Yinghui
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913066644406272
author Zhang, Zhang
Zeng, Yifeng
Jiang, Houshi
Pan, Yinghui
author_facet Zhang, Zhang
Zeng, Yifeng
Jiang, Houshi
Pan, Yinghui
contents WeatherSeg, an advanced semi-supervised segmentation framework, addresses autonomous driving's environmental perception challenges in adverse weather while reducing annotation costs. This framework integrates a Dual Teacher-Student Weight-Sharing Model (DTSWSM) that enables knowledge distillation from weather-affected images, and a Classifier Weight Updating Attention Mechanism (CWUAM) that dynamically adjusts classifier weights based on environmental attributes. Comprehensive evaluations demonstrate that WeatherSeg significantly outperforms baseline models in both accuracy and robustness across various weather conditions, including clear, rainy, cloudy, and foggy scenarios, establishing it as an effective solution for all-weather semantic segmentation in autonomous driving and related applications.
format Preprint
id arxiv_https___arxiv_org_abs_2604_22824
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle WeatherSeg: Weather-Robust Image Segmentation using Teacher-Student Dual Learning and Classifier-Updating Attention
Zhang, Zhang
Zeng, Yifeng
Jiang, Houshi
Pan, Yinghui
Computer Vision and Pattern Recognition
Artificial Intelligence
WeatherSeg, an advanced semi-supervised segmentation framework, addresses autonomous driving's environmental perception challenges in adverse weather while reducing annotation costs. This framework integrates a Dual Teacher-Student Weight-Sharing Model (DTSWSM) that enables knowledge distillation from weather-affected images, and a Classifier Weight Updating Attention Mechanism (CWUAM) that dynamically adjusts classifier weights based on environmental attributes. Comprehensive evaluations demonstrate that WeatherSeg significantly outperforms baseline models in both accuracy and robustness across various weather conditions, including clear, rainy, cloudy, and foggy scenarios, establishing it as an effective solution for all-weather semantic segmentation in autonomous driving and related applications.
title WeatherSeg: Weather-Robust Image Segmentation using Teacher-Student Dual Learning and Classifier-Updating Attention
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2604.22824