EUVIMEDEUVIMED entdecken
Crossref

Domain Adaptation Guided Infrared and Visible Image Fusion

Tianwei Guan, Haozhen Wei, Yuhan Zhou, Jun Ma, Zecheng Xu, Zhiying Jiang, Jinyuan Liu, Xingyuan Li

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (6) · 4376-4384

DOI: 10.1609/aaai.v40i6.42435 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Tianwei Guan und 7 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Infrared and Visible Image Fusion (IVIF) integrates complementary information from distinct modalities to enhance image quality. However, the effectiveness declines under unseen conditions such as novel weather or scenes, due to domain shifts primarily from variations of data distribution in the visible modality, while the infrared modality remains relatively stable. To overcome domain shifts caused by the imbalance between modalities during image fusion, we propose a Domain Adaptation Guided Infrared and Visible Image Fusion method, termed DAFusion, leveraging a dual-rank domain adapter to enable fast adaptation to diverse adverse conditions during image fusion. Specifically, trainable low-rank and high-rank embedding spaces are respectively used to capture knowledge common across domains (domain-shared) and those unique to target domains (domain-specific). To leverage the dual-rank adapter more effectively, we develop a homeostatic knowledge allotment strategy to integrate the distinct types of knowledge dynamically based on the uncertainty value of target domains. Since domain adaptation typically optimizes for feature alignment across domains and emphasizes invariance rather than preserving specific cues critical for image fusion, while the fusion objective requires retaining discriminative and complementary features, a conflict between the two modules appears. To reconcile this, we further adopt a bi-level optimization framework that structurally decouples the two objectives, enabling the fusion module to steer the adaptation process while benefiting in return from domain-aligned representations. Experimental results on three benchmarks demonstrate that our method significantly outperforms state-of-the-art approaches, achieving both an enhancement in fusion quality and an improvement on subsequent high-level tasks.

Zitieren

APA

Guan, T., Wei, H., Zhou, Y., Ma, J., Xu, Z., Jiang, Z., Liu, J., & Li, X. (2026). Domain Adaptation Guided Infrared and Visible Image Fusion. Proceedings of the AAAI Conference on Artificial Intelligence, 40(6), 4376-4384. https://doi.org/10.1609/aaai.v40i6.42435

Vancouver

Guan T, Wei H, Zhou Y, Ma J, Xu Z, Jiang Z, et al. Domain Adaptation Guided Infrared and Visible Image Fusion. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(6):4376-4384. doi:10.1609/aaai.v40i6.42435

BibTeX
@article{Guan2026,
  author = {Guan, Tianwei and Wei, Haozhen and Zhou, Yuhan and Ma, Jun and Xu, Zecheng and Jiang, Zhiying and Liu, Jinyuan and Li, Xingyuan},
  title = {Domain Adaptation Guided Infrared and Visible Image Fusion},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {6},
  pages = {4376--4384},
  doi = {10.1609/aaai.v40i6.42435}
}
Kostenlos starten →