DyFCLT：面向多模态小目标检测的动态频率解耦跨模态学习 Transformer
DyFCLT: Dynamic Frequency-Decoupled Cross-Modal Learning Transformer for Multimodal Tiny Object Detection
把频域子带解耦后做跨模态注意力，为 RGBT 小目标检测提供了一条可复用的思路：按频率成分而非空间位置对齐模态，可直接迁移到其他多模态密集预测任务。
原文依据 tiny objects in both RGB and infrared modalities contain richer mid- and high-frequency components as object size decreases
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论多模态小目标检测在现实应用中起着关键作用，但由于目标表征微弱以及跨模态干扰复杂，该任务仍极具挑战性。现有的面向小目标检测的频域方法在很大程度上仍局限于可见光模态，并忽视了多模态场景中互补的跨模态频率线索。本文研究面向 RGBT 小目标检测的跨模态频率学习。通过频率特性分析，我们发现随着目标尺寸减小，RGB 与红外两种模态中的小目标都包含更丰富的中频与高频成分。受此观察启发，我们提出动态频率解耦跨模态学习 Transformer（DyFCLT）。具体而言，DyFCLT 引入动态频带解耦跨模态注意力（DFCA）机制，在动态频率子带上进行细粒度的跨模态交互；并引入选择性平滑增强（SSE）模块，在多尺度融合过程中抑制背景噪声并增强前景响应。在两个 RGBT 小目标检测基准和一个通用尺度基准上的大量实验表明，DyFCLT 取得了最优性能，并在不同尺度与场景下展现出强泛化能力。
英文原文摘要 1315 字符
Multimodal tiny object detection plays a critical role in real-world applications, yet remains highly challenging due to weak target representations and complex cross-modal interference. Existing frequency-domain methods for tiny object detection are still largely limited to the visible modality and overlook complementary cross-modal frequency cues in multimodal scenes. In this paper, we investigate cross-modal frequency learning for RGBT tiny object detection. Through frequency characteristic analysis, we find that tiny objects in both RGB and infrared modalities contain richer mid- and high-frequency components as object size decreases. Motivated by this observation, we propose a Dynamic Frequency-Decoupled Cross-Modal Learning Transformer (DyFCLT). Specifically, DyFCLT introduces a Dynamic Frequency-Band Decoupled Cross-Modal Attention (DFCA) mechanism to perform fine-grained cross-modal interaction across dynamic frequency sub-bands, and a Selective Smoothing Enhancement (SSE) module to suppress background noise and enhance foreground responses during multi-scale fusion. Extensive experiments on two RGBT tiny object detection benchmarks and one general-scale benchmark demonstrate that DyFCLT achieves state-of-the-art performance with strong generalization across different scales and scenes.