Enhancing RGB-IR object detection: a frozen backbone approach with multi-receptive field attention
The Visual Computer · 2026-02 · 42 (3)
DOI: 10.1007/s00371-026-04378-1 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Visual Computer, online erschienen am 12.02.2026. Verfasst von Bingyu Lu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Recent advancements in multimodal object detection have predominantly relied on end-to-end training paradigms, which, while effective, demand substantial computational resources and risk feature degradation. To address these challenges, we propose a frozen backbone paradigm, preserving pretrained representations as stable semantic anchors for efficient multimodal fusion. Our approach introduces a lightweight multi-receptive field attention (MRFA) mechanism, enhancing feature interaction and representation diversity without exhaustive retraining. Experiments on the FLIR Aligned and M3\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$^3$$\end{document}FD dataset demonstrate consistent improvements over state-of-the-art end-to-end models, highlighting the potential of pretrained backbones coupled with adaptive attention mechanisms for robust multimodal object detection. The project code is released at https://github.com/LuBingyu11/MRFA.
Zitieren
APA
Lu, B., Liu, H., & Watanabe, H. (2026). Enhancing RGB-IR object detection: a frozen backbone approach with multi-receptive field attention. The Visual Computer, 42(3). https://doi.org/10.1007/s00371-026-04378-1
Vancouver
Lu B, Liu H, Watanabe H. Enhancing RGB-IR object detection: a frozen backbone approach with multi-receptive field attention. The Visual Computer. 2026;42(3). doi:10.1007/s00371-026-04378-1
BibTeX
@article{Lu2026,
author = {Lu, Bingyu and Liu, Haoyuan and Watanabe, Hiroshi},
title = {Enhancing RGB-IR object detection: a frozen backbone approach with multi-receptive field attention},
journal = {The Visual Computer},
year = {2026},
volume = {42},
number = {3},
doi = {10.1007/s00371-026-04378-1}
}
EUVIMED