CollabOD: Collaborative Multi-Backbone with Cross-scale Vision for UAV Small Object Detection
Not on the map. Why?
Abstract (arXiv)
Small object detection in unmanned aerial vehicle (UAV) imagery is challenging because high-altitude viewpoints produce severe scale variation, weak structural cues, and tight computational budgets. Existing lightweight detectors usually fuse multi-scale features after downsampling, where boundary and texture details have already been attenuated and heterogeneous feature streams may be spatially misaligned. To address these issues, we propose CollabOD, a collaborative detection framework that preserves structural details, aligns cross-path features before fusion, and keeps the detection head lightweight at inference time. CollabOD combines a Dual-Path Fusion Stem, a Dense Aggregation Block, a Bilateral Reweighting Module, and a Unified Detail-Aware Head to strengthen localization-oriented representation while limiting extra computation. On VisDrone, CollabOD obtains 52.4 AP50, 30.8 AP75, and 29.9 AP50:95 with 65.5 GFLOPs; on UAVDT it reaches 31.2 AP50 and 17.4 AP50:95; and on AI-TOD it reaches 45.4 AP50 and 20.0 AP50:95 at 137 FPS. The code is available at: https://github.com/Bai-Xuecheng/CollabOD.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 36 of its 52 references that are in the map. First posted on arXiv 6 Mar 2026.
Builds on
36 of 52 references.
References · 36
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2016Feature Pyramid Networks for Object Detectioncited by 5,036
- 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,368
- 2018Path Aggregation Network for Instance Segmentationcited by 798
- 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 515
- 2019Distance-IoU Loss: Faster and Better Learning for Bounding Box Regressioncited by 459
- 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
- 2020Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detectioncited by 409
- 2025YOLOv12: Attention-Centric Real-Time Object Detectorscited by 305
- 2019NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detectioncited by 291
- 2020Detection and Tracking Meet Drones Challengecited by 263
- 2018The Unmanned Aerial Vehicle Benchmark: Object Detection and Trackingcited by 208
24 more
- 2017Drone-based Object Counting by Spatially Regularized Regional Proposal Networkcited by 156
- 2021Focal and Global Knowledge Distillation for Detectorscited by 142
- 2019Clustered Object Detection in Aerial Imagescited by 83
- 2022PP-YOLOE: An evolved version of YOLOcited by 75
- 2021QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detectioncited by 70
- 2019Learning Spatial Fusion for Single-Shot Object Detectioncited by 59
- 2021Focal and Efficient IOU Loss for Accurate Bounding Box Regressioncited by 57
- 2019AugFPN: Improving Multi-scale Feature Learning for Object Detectioncited by 55
- 2022SuperYOLO: Super Resolution Assisted Object Detection in Multimodal Remote Sensing Imagerycited by 47
- 2023Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Imagescited by 41
- 2023YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detectioncited by 33
- 2023AFPN: Asymptotic Feature Pyramid Network for Object Detectioncited by 17
- 2025Small Object Detection: A Comprehensive Survey on Challenges, Techniques and Real-World Applicationscited by 16
- 2024ESOD: Efficient Small Object Detection on High-Resolution Imagescited by 15
- 2025UAV-DETR: Efficient End-to-End Object Detection for Unmanned Aerial Vehicle Imagerycited by 15
- 2024Cross-Layer Feature Pyramid Transformer for Small Object Detection in Aerial Imagescited by 11
- 2025LEGNet: A Lightweight Edge-Gaussian Network for Low-Quality Remote Sensing Image Object Detectioncited by 7
- 2025MHAF-YOLO: Multi-Branch Heterogeneous Auxiliary Fusion YOLO for accurate object detectioncited by 4
- 2025YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detectioncited by 4
- 2023Task-Specific Context Decoupling for Object Detectioncited by 3
- 2026EFSI-DETR: Efficient Frequency-Semantic Integration for Real-Time Small Object Detection in UAV Imagerycited by 3
- 2025Efficient Feature Fusion for UAV Object Detectioncited by 2
- 2025AD-Det: Boosting Object Detection in UAV Images with Focused Small Objects and Balanced Tail Classescited by 2
- 2025MGDFIS: Multi-scale Global-detail Feature Integration Strategy for Small Object Detectioncited by 1
Built on by
Not cited yet.