Research
FSDETR: Frequency-Spatial Feature Enhancement for Small Object Detection
arXiv:2604.14884v1 Announce Type: new Abstract: Small object detection remains a significant challenge due to feature degradation from downsampling, mutual occlusion in dense clusters, and complex bac
arXiv:2604.14884v1 Announce Type: new Abstract: 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.
Related
- WUTDet: A 100K-Scale Ship Detection Dataset and Benchmarks with Dense Small Objects
- A3-FPN: Asymptotic Content-Aware Pyramid Attention Network for Dense Visual Prediction
- Sparse Hypergraph-Enhanced Frame-Event Object Detection with Fine-Grained MoE
- Dual-R-DETR: Resolving Query Competition with Pairwise Routing in Transformer Decoders
Source: arXiv cs.CV | 2026-04-17