mlsanityData to 14 Oct 2026

ScopeMamba-YOLO: Widening the Perceptual Scope Inward and Outward for Small Object Detection in Remote Sensing Imagery

arXiv 2609.10156 ↗First posted 9 Sep 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Small object detection in unmanned aerial vehicle (UAV) and remote sensing imagery requires preserving high-resolution detail while modeling long-range context. Adding a stride-4 detection level and removing the stride-32 stage benefits tiny targets but weakens peripheral spatial support, whereas directly inserting selective scanning into the main feature path can interfere with weak local cues. We propose ScopeMamba-YOLO, built around an off-path, zero-gated selective-scanning principle that decouples contextual modeling from the convolutional stream. The principle is instantiated by a Cascaded Global-Context Module (CGCM) in the backbone and a Selective-Scan PAN (SS-PAN) in the neck. An Adaptive Multi-scale Strip (AMS) Block reduces the cost of high-resolution feature extraction, while a Scale-Adaptive DFL (SA-DFL) head reallocates distributional support and regression capacity across scales with only 0.008M additional parameters. Controlled experiments show that matched main-path selective scanning reduces mAP50 by 0.98 pp, whereas off-path CGCM improves the final configuration by 0.67 pp over the three-seed no-CGCM mean; operator controls indicate that this gain is not explained by auxiliary branch capacity alone. ERF analysis further shows that the complete context pathway increases the peripheral energy ratio from 0.008 to 0.090 at stride 8. On VisDrone-2019, ScopeMamba-S achieves 50.8% mAP50 with 3.57M parameters, exceeding YOLOv8s by 10.8 pp while using 32% of its parameters; ScopeMamba-M reaches 52.6% mAP50 with 6.48M parameters. Consistent improvements are also observed on AI-TOD, especially for very-tiny and tiny objects.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 55 of its 81 references that are in the map. First posted on arXiv 9 Sep 2026.

Builds on

55 of 81 references.

References · 55

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  6. 2020End-to-End Object Detection with Transformerscited by 7,414
  7. 2017Mask R-CNNcited by 7,277
  8. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  9. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  10. 2017Squeeze-and-Excitation Networkscited by 4,789
  11. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  12. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
38 more
  1. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  2. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  3. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  4. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
  5. 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 1,336
  6. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,056
  7. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,020
  8. 2024VMamba: Visual State Space Modelcited by 969
  9. 2018Path Aggregation Network for Instance Segmentationcited by 798
  10. 2017DOTA: A Large-scale Dataset for Object Detection in Aerial Imagescited by 623
  11. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 533
  12. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 515
  13. 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 425
  14. 2024YOLOv11: An Overview of the Key Architectural Enhancementscited by 425
  15. 2020Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detectioncited by 409
  16. 2019Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmarkcited by 340
  17. 2020Detection and Tracking Meet Drones Challengecited by 263
  18. 2022Towards Large-Scale Small Object Detection: Survey and Benchmarkscited by 122
  19. 2024ChangeMamba: Remote Sensing Change Detection With Spatiotemporal State Space Modelcited by 120
  20. 2022Slicing Aided Hyper Inference and Fine-tuning for Small Object Detectioncited by 105
  21. 2023Large Selective Kernel Network for Remote Sensing Object Detectioncited by 98
  22. 2024RSMamba: Remote Sensing Image Classification with State Space Modelcited by 95
  23. 2019Clustered Object Detection in Aerial Imagescited by 83
  24. 2021TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarioscited by 83
  25. 2024RS-Mamba for Large Remote Sensing Image Dense Predictioncited by 81
  26. 2016A Survey on Object Detection in Optical Remote Sensing Imagescited by 78
  27. 2024Pan-Mamba: Effective pan-sharpening with State Space Modelcited by 73
  28. 2021QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detectioncited by 70
  29. 2024Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Modelcited by 62
  30. 2024MiM-ISTD: Mamba-in-Mamba for Efficient Infrared Small Target Detectioncited by 60
  31. 2023Learning to Upsample by Learning to Samplecited by 57
  32. 2020Density Map Guided Object Detection in Aerial Imagescited by 56
  33. 2022Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmarkcited by 56
  34. 2024Poly Kernel Inception Network for Remote Sensing Detectioncited by 52
  35. 2023Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Imagescited by 41
  36. 2023Efficient Multi-Scale Attention Module with Cross-Spatial Learningcited by 41
  37. 2021UFPMP-Det: Toward Accurate and Efficient Object Detection on Drone Imagerycited by 34
  38. 2024Mamba YOLO: A Simple Baseline for Object Detection with State Space Modelcited by 19

50 most cited of 55 All 55 (JSON)

Built on by

Not cited yet.