FogTTA: Online Test-Time Adaptation for Robust Transformer-based Object Detection in Foggy Weather

Ali Abedi, Q. M. Jonathan Wu, Ning Zhang, Shiqi Tian
Proceedings of the The 39th Canadian Conference on Artificial Intelligence, PMLR 318:13-24, 2026.

Abstract

Object detection models for autonomous driving commonly experience substantial performance drops when deployed under adverse weather due to the domain shift between training data and real-world operating conditions. This degradation is especially evident when models trained on clear-weather images encounter foggy environments with reduced visibility and contrast. To address this challenge, we introduce FogTTA, an online test-time adaptation framework designed to improve the robustness of Transformer-based object detectors in fog. Using RF-DETR as the underlying object detector, FogTTA enables real-time adaptation to the streaming target domain without requiring source data or retraining. The framework follows a teacher–student design, where the deployed model serves as the teacher and generates pseudo labels from weakly augmented target inputs. These predictions are subsequently refined through non-maximum suppression and confidence filtering. The student model then learns from strongly augmented target sample using the Varifocal loss to mitigate pseudo-label noise. The teacher is updated via exponential moving averaging to ensure stable and continuous adaptation. Experiments show that FogTTA outperforms prior baselines, delivering improved detection accuracy and stability while maintaining real-time performance.

Cite this Paper

BibTeX
@InProceedings{pmlr-v318-abedi26a, title = {FogTTA: Online Test-Time Adaptation for Robust Transformer-based Object Detection in Foggy Weather}, author = {Abedi, Ali and Wu, Q. M. Jonathan and Zhang, Ning and Tian, Shiqi}, booktitle = {Proceedings of the The 39th Canadian Conference on Artificial Intelligence}, pages = {13--24}, year = {2026}, editor = {Bouzar-Benlabiod, Lydia and Leung, Carson}, volume = {318}, series = {Proceedings of Machine Learning Research}, month = {25--29 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v318/main/assets/abedi26a/abedi26a.pdf}, url = {https://proceedings.mlr.press/v318/abedi26a.html}, abstract = {Object detection models for autonomous driving commonly experience substantial performance drops when deployed under adverse weather due to the domain shift between training data and real-world operating conditions. This degradation is especially evident when models trained on clear-weather images encounter foggy environments with reduced visibility and contrast. To address this challenge, we introduce FogTTA, an online test-time adaptation framework designed to improve the robustness of Transformer-based object detectors in fog. Using RF-DETR as the underlying object detector, FogTTA enables real-time adaptation to the streaming target domain without requiring source data or retraining. The framework follows a teacher–student design, where the deployed model serves as the teacher and generates pseudo labels from weakly augmented target inputs. These predictions are subsequently refined through non-maximum suppression and confidence filtering. The student model then learns from strongly augmented target sample using the Varifocal loss to mitigate pseudo-label noise. The teacher is updated via exponential moving averaging to ensure stable and continuous adaptation. Experiments show that FogTTA outperforms prior baselines, delivering improved detection accuracy and stability while maintaining real-time performance.} }
Endnote
%0 Conference Paper %T FogTTA: Online Test-Time Adaptation for Robust Transformer-based Object Detection in Foggy Weather %A Ali Abedi %A Q. M. Jonathan Wu %A Ning Zhang %A Shiqi Tian %B Proceedings of the The 39th Canadian Conference on Artificial Intelligence %C Proceedings of Machine Learning Research %D 2026 %E Lydia Bouzar-Benlabiod %E Carson Leung %F pmlr-v318-abedi26a %I PMLR %P 13--24 %U https://proceedings.mlr.press/v318/abedi26a.html %V 318 %X Object detection models for autonomous driving commonly experience substantial performance drops when deployed under adverse weather due to the domain shift between training data and real-world operating conditions. This degradation is especially evident when models trained on clear-weather images encounter foggy environments with reduced visibility and contrast. To address this challenge, we introduce FogTTA, an online test-time adaptation framework designed to improve the robustness of Transformer-based object detectors in fog. Using RF-DETR as the underlying object detector, FogTTA enables real-time adaptation to the streaming target domain without requiring source data or retraining. The framework follows a teacher–student design, where the deployed model serves as the teacher and generates pseudo labels from weakly augmented target inputs. These predictions are subsequently refined through non-maximum suppression and confidence filtering. The student model then learns from strongly augmented target sample using the Varifocal loss to mitigate pseudo-label noise. The teacher is updated via exponential moving averaging to ensure stable and continuous adaptation. Experiments show that FogTTA outperforms prior baselines, delivering improved detection accuracy and stability while maintaining real-time performance.
APA
Abedi, A., Wu, Q.M.J., Zhang, N. & Tian, S.. (2026). FogTTA: Online Test-Time Adaptation for Robust Transformer-based Object Detection in Foggy Weather. Proceedings of the The 39th Canadian Conference on Artificial Intelligence, in Proceedings of Machine Learning Research 318:13-24 Available from https://proceedings.mlr.press/v318/abedi26a.html.

Related Material