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

• URL: http://arxiv.org/abs/2609.10156v1
• Date: Wed, 09 Sep 2026 13:32:46 GMT
• Title: ScopeMamba-YOLO: Widening the Perceptual Scope Inward and Outward for Small Object Detection in Remote Sensing Imagery
• Abstract summary: Small object detection in unmanned aerial vehicle (UAV) and remote sensing imagery requires preserving high-resolution detail while modeling long-range context.<n>We propose ScopeMamba-YOLO, built around an off-path, zero-gated selective-scanning principle that decouples contextual modeling from the convolutional stream.<n>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.
• Score: 2.3496832983179807
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• LCMamNet: A Lightweight Cross-scale Mamba Network for Infrared Small Target Detection [53.811713750107934]
  We propose LCMamNet, a lightweight cross-scale Mamba network for infrared small target detection.<n>A compact hierarchical encoder with cross-shaped directional bottleneck residual blocks strengthens direction-sensitive target structures.<n>Experiments on IRSTD-1k, NUAA-SIRST, and NUDT-SIRST show that the proposed network achieves mIoU scores of 71.25%, 79.60%, and 95.58%, respectively.
  arXiv  Detail & Related papers  (2026-07-27T09:06:14Z)
• LLM-Empowered Multimodal Fusion Framework for Autonomous Driving: Semantic Enhancement and Channel-Adaptive Design [56.76240343283953]
  We propose a Large Language Model-centric Semantic-layer Channel-aware Integrated Perception framework.<n>It fuses a local visual stream with a quality-varying external radar stream used to cover perception-blind spots.<n>Experiments on nuScenes and VIRAT validate our approach.
  arXiv  Detail & Related papers  (2026-07-02T06:44:02Z)
• LocalNav: Distilling Frontier VLMs and Embodied RL for On-Device Object Goal Navigation [53.88286427894783]
  Vision Language Models (VLMs) have emerged in the robotic domain as a powerful tool that enables environmental perception with language context.<n>Yet, their computational footprint typically confines them to cloud execution, hindering low-latency inference with local deployment on resource-constrained robots.<n>We present a distillation strategy that transfers complex spatial-semantic reasoning from large frontier models into a lightweight, 4B- parameter local VLM for edge execution on embedded GPU devices.
  arXiv  Detail & Related papers  (2026-06-26T09:11:59Z)
• ArcGate: Adaptive Arctangent Gated Activation [62.5098969984518]
  This paper proposes the Adaptive Arctangent Gated Activation function, a flexible formulation that generates a broad spectrum of activation shapes.<n>We evaluate ArcGate on three widely used remote sensing benchmarks: PatternNet, UC Merced Land Use, and the 13-band EuroSAT MSI multispectral dataset.
  arXiv  Detail & Related papers  (2026-05-14T08:00:46Z)
• Beyond Localization: A Comprehensive Diagnosis of Perspective-Conditioned Spatial Reasoning in MLLMs from Omnidirectional Images [52.50752250573993]
  Multimodal Large Language Models (MLLMs) show strong visual perception, yet remain limited in reasoning about space under changing viewpoints.<n>We study this challenge as Perspective-Conditioned Spatial Reasoning (PCSR) in 360-degree omnidirectional images.<n>We introduce PCSR-Bench, a diagnostic benchmark of 84,373 question-answer pairs from 2,600 omnidirectional images.
  arXiv  Detail & Related papers  (2026-05-12T17:11:17Z)
• DroneScan-YOLO: Redundancy-Aware Lightweight Detection for Tiny Objects in UAV Imagery [0.0]
  DroneScan-YOLO is a holistic system contribution that addresses limitations through four coordinated design choices.<n>DroneScan-YOLO achieves 55.3% mAP@50 and 35.6% mAP@50-95, outperforming the YOLOv8s baseline by +16.6 and +12.3 points respectively.
  arXiv  Detail & Related papers  (2026-04-14T20:14:57Z)
• SCAFusion: A Multimodal 3D Detection Framework for Small Object Detection in Lunar Surface Exploration [18.857802421595235]
  This paper presents SCAFusion, a multimodal 3D object detection model tailored for lunar robotic missions.<n>With negligible increase in parameters, our model achieves 69.7% mAP and 72.1% NDS on the nuScenes validation set.<n>In simulated lunar environments built on Isaac Sim, SCAFusion achieves 90.93% mAP, outperforming the baseline by 11.5%.
  arXiv  Detail & Related papers  (2025-12-27T07:08:03Z)
• MRS-YOLO Railroad Transmission Line Foreign Object Detection Based on Improved YOLO11 and Channel Pruning [2.6795746856835785]
  We propose an improved algorithm MRS-YOLO based on YOLO11.<n>The mAP50 and mAP50:95 of the MRS-YOLO algorithm are improved to 94.8% and 86.4%, respectively.
  arXiv  Detail & Related papers  (2025-10-12T11:38:09Z)
• YOLOv11-Litchi: Efficient Litchi Fruit Detection based on UAV-Captured Agricultural Imagery in Complex Orchard Environments [6.862722449907841]
  This paper introduces YOLOv11-Litchi, a lightweight and robust detection model specifically designed for UAV-based litchi detection.<n>YOLOv11-Litchi achieves a parameter size of 6.35 MB - 32.5% smaller than the YOLOv11 baseline.<n>The model achieves a frame rate of 57.2 FPS, meeting real-time detection requirements.
  arXiv  Detail & Related papers  (2025-10-11T09:44:00Z)
• An Efficient Aerial Image Detection with Variable Receptive Fields [0.0]
  We propose a transformer-based detector incorporating three key components.<n>VRF-DETR achieves 51.4% mAPtextsubscript50 and 31.8% mAPtextsubscript50:95 with only 13.5M parameters.
  arXiv  Detail & Related papers  (2025-04-21T15:16:13Z)
• Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning [79.43940012723539]
  ADCLR is a self-supervised learning framework for learning accurate and dense vision representation. Our approach achieves new state-of-the-art performance for contrastive methods.
  arXiv  Detail & Related papers  (2023-06-23T07:38:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.