Scholarlink

<p>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 M<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(^3\)</EquationSource> <EquationSource Format="MATHML"><math> <mmultiscripts> <mrow /> <mrow /> <mn>3</mn> </mmultiscripts> </math></EquationSource> </InlineEquation>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 <a href="https://github.com/LuBingyu11/MRFA">https://github.com/LuBingyu11/MRFA</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Enhancing RGB-IR object detection: a frozen backbone approach with multi-receptive field attention

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月12日

查看全文
  • Bingyu Lu,
  • Haoyuan Liu,
  • Hiroshi Watanabe

摘要

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 M \(^3\) 3 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.