TTA-DAME: Test-Time Adaptation with Domain Augmentation and Model Ensemble for Dynamic Driving Conditions

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jeon, Dongjae, Kim, Taeheon, Cho, Seongwon, Seo, Minhyuk, Choi, Jonghyun
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908922461290496
author Jeon, Dongjae
Kim, Taeheon
Cho, Seongwon
Seo, Minhyuk
Choi, Jonghyun
author_facet Jeon, Dongjae
Kim, Taeheon
Cho, Seongwon
Seo, Minhyuk
Choi, Jonghyun
contents Test-time Adaptation (TTA) poses a challenge, requiring models to dynamically adapt and perform optimally on shifting target domains. This task is particularly emphasized in real-world driving scenes, where weather domain shifts occur frequently. To address such dynamic changes, our proposed method, TTA-DAME, leverages source domain data augmentation into target domains. Additionally, we introduce a domain discriminator and a specialized domain detector to mitigate drastic domain shifts, especially from daytime to nighttime conditions. To further improve adaptability, we train multiple detectors and consolidate their predictions through Non-Maximum Suppression (NMS). Our empirical validation demonstrates the effectiveness of our method, showing significant performance enhancements on the SHIFT Benchmark.
format Preprint
id arxiv_https___arxiv_org_abs_2508_12690
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TTA-DAME: Test-Time Adaptation with Domain Augmentation and Model Ensemble for Dynamic Driving Conditions
Jeon, Dongjae
Kim, Taeheon
Cho, Seongwon
Seo, Minhyuk
Choi, Jonghyun
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Test-time Adaptation (TTA) poses a challenge, requiring models to dynamically adapt and perform optimally on shifting target domains. This task is particularly emphasized in real-world driving scenes, where weather domain shifts occur frequently. To address such dynamic changes, our proposed method, TTA-DAME, leverages source domain data augmentation into target domains. Additionally, we introduce a domain discriminator and a specialized domain detector to mitigate drastic domain shifts, especially from daytime to nighttime conditions. To further improve adaptability, we train multiple detectors and consolidate their predictions through Non-Maximum Suppression (NMS). Our empirical validation demonstrates the effectiveness of our method, showing significant performance enhancements on the SHIFT Benchmark.
title TTA-DAME: Test-Time Adaptation with Domain Augmentation and Model Ensemble for Dynamic Driving Conditions
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2508.12690