EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hierarchical Domain Adaptation with Multi-Level Attention for RGB-Thermal Object Detection

Yunan Liu, Mingrong Gong, Chaoqi Chen

Journal of Intelligent Computing and Networking · 30.07.2026 · 2 (3) · 1-13

DOI: 10.64509/jicn.23.127 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Intelligent Computing and Networking, online erschienen am 30.07.2026. Verfasst von Yunan Liu und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cross-modal domain adaptation for RGB-to-Thermal object detection (DAOD) remains a challenging task due to the large modality gap, feature distribution mismatch, and limited supervision on the thermal domain. Conventional domain adaptation detectors often fail to capture consistent semantic representations across modalities, resulting in unstable adversarial learning and suboptimal detection accuracy. To address these challenges, we propose HDAM (Hierarchical Domain Adaptation with Multi-Level Attention), an enhanced domain-adaptive detection framework built upon Faster R-CNN. HDAM progressively aligns cross-domain features from low- to high-level representations through a hierarchical attention mechanism. Specifically, it comprises three key components: (1) Entropy-Guided Cross-level Attention (ECA), which leverages discriminator-derived entropy responses to reweight pixel- and mid-level features for more stable cross-modal encoding; (2) Multi-branch Global Semantics and Discriminator (MGSD), which performs global adversarial alignment and integrates multi-scale spatial information through attention-enhanced branches, while introducing an auxiliary image-level semantic consistency loss; and (3) Instance-Context Alignment (ICA), which fuses ROI-level and contextual embeddings and applies dual instance-level adversarial losses for precise fine-grained adaptation. Extensive experiments on benchmark RGB-Thermal datasets demonstrate that HDAM effectively bridges the modality gap and achieves improved cross-domain detection performance compared to recent DAOD methods.

Zitieren

APA

Liu, Y., Gong, M., & Chen, C. (2026). Hierarchical Domain Adaptation with Multi-Level Attention for RGB-Thermal Object Detection. Journal of Intelligent Computing and Networking, 2(3), 1-13. https://doi.org/10.64509/jicn.23.127

Vancouver

Liu Y, Gong M, Chen C. Hierarchical Domain Adaptation with Multi-Level Attention for RGB-Thermal Object Detection. Journal of Intelligent Computing and Networking. 2026;2(3):1-13. doi:10.64509/jicn.23.127

BibTeX
@article{Liu2026,
  author = {Liu, Yunan and Gong, Mingrong and Chen, Chaoqi},
  title = {Hierarchical Domain Adaptation with Multi-Level Attention for RGB-Thermal Object Detection},
  journal = {Journal of Intelligent Computing and Networking},
  year = {2026},
  volume = {2},
  number = {3},
  pages = {1--13},
  doi = {10.64509/jicn.23.127}
}
Kostenlos starten →