提升小物体检测性能，通过频域与空间特征协同增强。
FSDETR: Frequency-Spatial Feature Enhancement for Small Object Detection
- 引入频域-空间联合建模，融合多尺度细节信息。
- 仅用1470万参数，在VisDrone和TinyPerson上分别达13.9%和48.95%精度。
- 适合密集小目标场景，如无人机监控、行人检测等应用。
小物体检测因下采样导致的特征退化、密集区域相互遮挡及复杂背景干扰仍具挑战。本文提出基于RT-DETR基线的频率-空间特征增强框架FSDETR。通过协同建模机制，有效利用互补结构信息：空间分层注意力模块（SHAB）同时捕捉局部细节与全局依赖，强化语义表征；可变形注意力级内特征交互（DA-AIFI）通过动态采样聚焦信息丰富区域，缓解密集场景遮挡；频率-空间特征金字塔网络（FSFPN）借助跨域频空块（CFSB）实现频域滤波与空间边缘提取，保留细粒度特征。实验表明，仅含1470万参数的FSDETR在VisDrone 2019上达到13.9% APS，TinyPerson上达48.95% AP50 tiny，显著优于现有方法。代码与模型已开源。
原文摘要 · Abstract (English)
Small object detection remains a significant challenge due to feature degradation from downsampling, mutual occlusion in dense clusters, and complex background interference. To address these issues, this paper proposes FSDETR, a frequency-spatial feature enhancement framework built upon the RT-DETR baseline. By establishing a collaborative modeling mechanism, the method effectively leverages complementary structural information. Specifically, a Spatial Hierarchical Attention Block (SHAB) captures both local details and global dependencies to strengthen semantic representation. Furthermore, to mitigate occlusion in dense scenes, the Deformable Attention-based Intra-scale Feature Interaction (DA-AIFI) focuses on informative regions via dynamic sampling. Finally, the Frequency-Spatial Feature Pyramid Network (FSFPN) integrates frequency filtering with spatial edge extraction via the Cross-domain Frequency-Spatial Block (CFSB) to preserve fine-grained details. Experimental results show that with only 14.7M parameters, FSDETR achieves 13.9% APS on VisDrone 2019 and 48.95% AP50 tiny on TinyPerson, showing strong performance on small-object benchmarks. The code and models are available at https://github.com/YT3DVision/FSDETR.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。