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

TL;DR

WeatherSeg is a semi-supervised image segmentation framework that improves robustness and accuracy in adverse weather conditions for autonomous driving by using dual teacher-student models and dynamic classifier updates.

Contribution

It introduces a novel dual teacher-student model and a classifier weight updating mechanism to enhance weather-robust segmentation performance.

Findings

Outperforms baseline models in accuracy across various weather conditions.

Demonstrates significant robustness improvements in rainy, foggy, and cloudy scenarios.

Achieves state-of-the-art results in all-weather semantic segmentation tasks.

Abstract

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.