mlsanityData to 13 Oct 2026

FRFDet: Efficient UAV Small Object Detection with Symmetric Sampling and Scalable Fusion

arXiv 2607.04125 ↗First posted 5 Jul 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Small object detection in Unmanned Aerial Vehicle (UAV) imagery remains challenging under adverse conditions, including complex weather, low illumination, and sensor noise. These challenges mainly stem from severe background clutter, fine-grained detail degradation, and suboptimal semantic-spatial feature fusion, which jointly hinder robust small-object representation. To this end, we propose FRFDet, a lightweight yet effective single-stage detector tailored for UAV-based small object detection. FRFDet proposes two plug-and-play modules: Inverse Bidirectional Sampling (IBS) and Scale-Feature Relationship Cross-Fusion (SFRCF). IBS preserves critical spatial details via channel expansion-compression and bidirectional pattern reconstruction, improving feature alignment. SFRCF explicitly models scale-dependent fusion behaviors, revealing that inter-group element-wise multiplication favors compact models, while inter-group additive fusion benefits larger architectures. Extensive experiments on VisDrone, UAVDT, HazyDet, and MS COCO demonstrate that FRFDet achieves state-of-the-art performance among lightweight detectors with low computational cost, compact parameters, and fast inference, making it well suited for resource-constrained UAV platforms.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 45 of its 56 references that are in the map. First posted on arXiv 5 Jul 2026.

Builds on

45 of 56 references.

References · 45

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,043
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,550
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,111
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,625
  5. 2020End-to-End Object Detection with Transformerscited by 7,396
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,027
  7. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,658
  8. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,417
  9. 2025Qwen3-VL Technical Reportcited by 2,663
  10. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,575
  11. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,020
  12. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 979
33 more
  1. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  2. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 539
  3. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 530
  4. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 510
  5. 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 423
  6. 2020Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detectioncited by 408
  7. 2021Explaining Neural Scaling Lawscited by 355
  8. 2025YOLOv12: Attention-Centric Real-Time Object Detectorscited by 302
  9. 2019RepPoints: Point Set Representation for Object Detectioncited by 264
  10. 2021TOOD: Task-aligned One-stage Object Detectioncited by 218
  11. 2018The Unmanned Aerial Vehicle Benchmark: Object Detection and Trackingcited by 207
  12. 2019Feature Selective Anchor-Free Module for Single-Shot Object Detectioncited by 139
  13. 2019CARAFE: Content-Aware ReAssembly of FEaturescited by 119
  14. 2022Slicing Aided Hyper Inference and Fine-tuning for Small Object Detectioncited by 104
  15. 2019Clustered Object Detection in Aerial Imagescited by 83
  16. 2021QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detectioncited by 70
  17. 2023YOLOv6 v3.0: A Full-Scale Reloadingcited by 58
  18. 2023Learning to Upsample by Learning to Samplecited by 57
  19. 2020Density Map Guided Object Detection in Aerial Imagescited by 56
  20. 2023Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanismcited by 51
  21. 2025Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videoscited by 49
  22. 2023Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Imagescited by 41
  23. 2021Disentangle Your Dense Object Detectorcited by 37
  24. 2021UFPMP-Det: Toward Accurate and Efficient Object Detection on Drone Imagerycited by 34
  25. 2024Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computationcited by 29
  26. 2020HRDNet: High-resolution Detection Network for Small Objectscited by 25
  27. 2023AFPN: Asymptotic Feature Pyramid Network for Object Detectioncited by 17
  28. 2024ESOD: Efficient Small Object Detection on High-Resolution Imagescited by 15
  29. 2024HazyDet: Open-Source Benchmark for Drone-View Object Detection with Depth-Cues in Hazy Scenescited by 15
  30. 2022Centralized Feature Pyramid for Object Detectioncited by 13
  31. 2024YOLC: You Only Look Clusters for Tiny Object Detection in Aerial Imagescited by 11
  32. 2024RemDet: Rethinking Efficient Model Design for UAV Object Detectioncited by 9
  33. 2026PersonalQ: Select, Quantize, and Serve Personalized Diffusion Models for Efficient Inferencecited by 6

Built on by

Not cited yet.