YolovN-CBi: A Lightweight and Efficient Architecture for Real-Time Detection of Small UAVs
cs.CV
Submitted: 2025-12-19
Updated: 2026-09-21
Comments: This manuscript has been submitted to the journal Computer Optics and is currently under review
Code: https://github.com/ultralytics/yolov5
License: http://creativecommons.org/licenses/by/4.0/
The gist: Unmanned Aerial Vehicles, commonly known as, drones pose increasing risks in civilian and defense settings, demanding accurate and real-time drone detection systems.
Terminology
Abstract
Unmanned Aerial Vehicles, commonly known as, drones pose increasing risks in civilian and defense settings, demanding accurate and real-time drone detection systems. However, detecting drones is challenging because of their small size, rapid movement, and low visual contrast. A modified architecture of YolovN called the YolovN-CBi is proposed that incorporates the Convolutional Block Attention Module (CBAM) and the Bidirectional Feature Pyramid Network (BiFPN) to improve sensitivity to small object detections. A curated training dataset consisting of 28K images is created with various flying objects and a local test dataset is collected with 2500 images consisting of very small drone objects. The proposed architecture is evaluated on four benchmark datasets, along with the local test dataset. The baseline Yolov5 and the proposed Yolov5-CBi architecture outperform newer Yolo versions, including Yolov8 and Yolov12, in the speed-accuracy trade-off for small object detection. Four other variants of the proposed CBi architecture are also proposed and evaluated, which vary in the placement and usage of CBAM and BiFPN. These variants are further distilled using knowledge distillation techniques for edge deployment, using a Yolov5m-CBi teacher and a Yolov5n-CBi student. The distilled model achieved a mA@P0.5:0.9 of 0.6573, representing a 6.51% improvement over the teacher's score of 0.6171, highlighting the effectiveness of the distillation process. The distilled model is 82.9% faster than the baseline model, making it more suitable for real-time drone detection. These findings highlight the effectiveness of the proposed CBi architecture, together with the distilled lightweight models in advancing efficient and accurate real-time detection of small UAVs.
Sources
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- EfficientDet: Scalable and Efficient Object Detection
- Distilling the Knowledge in a Neural Network
- Mask R-CNN
- YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications
- YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
- YOLOv10: Real-Time End-to-End Object Detection
- YOLOv11: An Overview of the Key Architectural Enhancements
- YOLOv12: Attention-Centric Real-Time Object Detectors
- YOLO Evolution: A Comprehensive Benchmark and Architectural Review of YOLOv12, YOLO11, and Their Previous Versions
- A Decade of You Only Look Once (YOLO) for Object Detection: A Review
- Small Object Detection: A Comprehensive Survey on Challenges, Techniques and Real-World Applications
- Centerness-based Instance-aware Knowledge Distillation with Task-wise Mutual Lifting for Object Detection on Drone Imagery
- End-to-End Object Detection with Transformers
- Anti-UAV: A Large Multi-Modal Benchmark for UAV Tracking
- Vision-based Anti-UAV Detection and Tracking
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models