EUVIMEDEUVIMED entdecken
Crossref

Shared & Domain Self-Adaptive Experts with Frequency-Aware Discrimination for Continual Test-Time Adaptation

Jianchao Zhao, Chenhao Ding, SongLin Dong, Jiangyang Li, Qiang Wang, Yuhang He, Yihong Gong

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (34) · 28697-28705

DOI: 10.1609/aaai.v40i34.40102 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Jianchao Zhao und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper focuses on the Continual Test-Time Adaptation (CTTA) task, aiming to enable an agent to continuously adapt to evolving target domains while retaining previously acquired domain knowledge for effective reuse when those domains reappear. Existing shared-parameter paradigms struggle to balance adaptation and forgetting, leading to decreased efficiency and stability. To address this, we propose a frequency-aware shared and self-adaptive expert framework, consisting of two key components: (i) a dual-branch expert architecture that extracts general features and dynamically models domain-specific representations, effectively reducing cross-domain interference and repetitive learning cost; and (ii) an online Frequency-aware Domain Discriminator (FDD), which leverages the robustness of low-frequency image signals for online domain shift detection, guiding dynamic allocation of expert resources for more stable and realistic adaptation. Additionally, we introduce a Continual Repeated Shifts (CRS) benchmark to simulate periodic domain changes for more realistic evaluation. Experimental results show that our method consistently outperforms existing approaches on both classification and segmentation CTTA tasks under standard and CRS settings, with ablations and visualizations confirming its effectiveness and robustness.

Zitieren

APA

Zhao, J., Ding, C., Dong, S., Li, J., Wang, Q., He, Y., & Gong, Y. (2026). Shared & Domain Self-Adaptive Experts with Frequency-Aware Discrimination for Continual Test-Time Adaptation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(34), 28697-28705. https://doi.org/10.1609/aaai.v40i34.40102

Vancouver

Zhao J, Ding C, Dong S, Li J, Wang Q, He Y, et al. Shared & Domain Self-Adaptive Experts with Frequency-Aware Discrimination for Continual Test-Time Adaptation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(34):28697-28705. doi:10.1609/aaai.v40i34.40102

BibTeX
@article{Zhao2026,
  author = {Zhao, Jianchao and Ding, Chenhao and Dong, SongLin and Li, Jiangyang and Wang, Qiang and He, Yuhang and Gong, Yihong},
  title = {Shared & Domain Self-Adaptive Experts with Frequency-Aware Discrimination for Continual Test-Time Adaptation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {34},
  pages = {28697--28705},
  doi = {10.1609/aaai.v40i34.40102}
}
Kostenlos starten →