EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CAC-Net: Convolutional Additive Cross-Modal Fusion for Real-Time RGB-T Object Detection

Ziwen Zhu, Xiaoou Song, Guangming Zhou, Mingmei Chen, Xiaobing Deng

IEEE Access · 2026 · 14 · 81813-81823

DOI: 10.1109/access.2026.3694554 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Ziwen Zhu und 4 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Real-time RGB-T object detection faces significant challenges from illumination variations, background thermal clutter, and strict computational constraints. To tackle these, we propose CAC-Net, an efficient convolutional additive cross-modal fusion network that leverages complementary visible and thermal infrared modalities while maintaining linear computational complexity in the fusion pipeline. Our key contributions are threefold: 1) integrating Pinwheel-shaped convolution in the early dual-stream backbone to enhance discriminative representation of faint thermal cues and fine-grained RGB textures; 2) enabling global dependency modeling via a cross-modal additive attention fusion module with explicit spatial and channel alignment; 3) introducing a consensus-driven shared straight-through Top-K sparsification mechanism that adaptively suppresses modality-specific noise while remaining differentiable. Extensive experiments on challenging RGB-T benchmarks demonstrate that CAC-Net significantly outperforms current publicly available state-of-the-art methods in both accuracy and efficiency, establishing a new paradigm for robust, real-time, and resource-efficient multimodal perception. The code will be available at https://github.com/ZZWHLL/CAC-Net

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zhu, Z., Song, X., Zhou, G., Chen, M., & Deng, X. (2026). CAC-Net: Convolutional Additive Cross-Modal Fusion for Real-Time RGB-T Object Detection. IEEE Access, 14, 81813-81823. https://doi.org/10.1109/access.2026.3694554

Vancouver

Zhu Z, Song X, Zhou G, Chen M, Deng X. CAC-Net: Convolutional Additive Cross-Modal Fusion for Real-Time RGB-T Object Detection. IEEE Access. 2026;14:81813-81823. doi:10.1109/access.2026.3694554

BibTeX
@article{Zhu2026,
  author = {Zhu, Ziwen and Song, Xiaoou and Zhou, Guangming and Chen, Mingmei and Deng, Xiaobing},
  title = {CAC-Net: Convolutional Additive Cross-Modal Fusion for Real-Time RGB-T Object Detection},
  journal = {IEEE Access},
  year = {2026},
  volume = {14},
  pages = {81813--81823},
  doi = {10.1109/access.2026.3694554}
}
Kostenlos starten →