The impact of burn-in on semi-supervised single-stage object detection on small military datasets
conference paper
Semi-Supervised Object Detection (SSOD) aims to improve object detection performance by leveraging both labeled and (large amounts of) unlabeled data. By reducing the reliance on labeled data, SSOD enables faster model development and quicker deployment to the field, allowing systems to rapidly adapt to new environments or mission-specific scenarios with minimal annotation effort. While SSOD has demonstrated success in enhancing the performance of object detection models, ranging from two-stage detectors like R-CNN and DETR to more recent one-stage detectors such as YOLO, existing research has primarily focused on commonly studied benchmark datasets like PASCAL VOC and MS COCO. To the best of our knowledge, its effectiveness on domain-specific and smaller military relevant datasets has not been thoroughly evaluated. In this work, we investigate the performance of SSOD using YOLOv5 on three (military-relevant) use-case datasets: air-to-ground dataset VisDrone2019-DET, ground-to-ground dataset Automatic Target Recognition (ATR) Algorithm Development Image Database, our own in-house recorded and annotated proprietary military air-to-ground dataset, and our own internet crowd sourced Russian-Ukrainian War dataset containing ground-toground and air-to-ground imagery. We artificially limit the the labeled training data from 66% up to 1%, while treating the remainder as unlabeled. Our results show that SSOD consistently improves object detection performance across all datasets and label proportions compared to training without unlabeled data. Additionally, we find that the choice of burn-in epochs (the point at which labeled pretraining transitions to semi-supervised training) significantly impacts final performance. The optimal burn-in epoch is not necessarily the best performing validation epoch, highlighting the need for a careful burn-in approach.
Topics
Air-to-Ground ImageryEDF STOREGround-to-Ground ImagerySemi-Supervised learningSemi-Supervised Object DetectionYOLOBenchmarkingComputer visionImage annotationLabeled dataLearning algorithmsMilitary photographyObject detectionObject recognitionBurn-inPerformanceSemi-supervisedSemi-supervised object detectionImage enhancement
TNO Identifier
1024193
ISSN
0277786X
ISBN
978-151069297-8
Publisher
The International Society for Optical Engineering
Article nr.
1367905
Source title
Proceedings Artificial Intelligence for Security and Defence Applications III, Madrid, Spain, 16-18 September 2025
Collation
13 p.
Files
To receive the publication files, please send an e-mail request to TNO Repository.