Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: P, Malaisree, S, Youwai, T, Kitkobsin, S, Janrungautai, D, Amorndechaphon, P, Rojanavasu
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2510.25140
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917052443262976
author P, Malaisree
S, Youwai
T, Kitkobsin
S, Janrungautai
D, Amorndechaphon
P, Rojanavasu
author_facet P, Malaisree
S, Youwai
T, Kitkobsin
S, Janrungautai
D, Amorndechaphon
P, Rojanavasu
contents Object detection in civil engineering applications is constrained by limited annotated data in specialized domains. We introduce DINO-YOLO, a hybrid architecture combining YOLOv12 with DINOv3 self-supervised vision transformers for data-efficient detection. DINOv3 features are strategically integrated at two locations: input preprocessing (P0) and mid-backbone enhancement (P3). Experimental validation demonstrates substantial improvements: Tunnel Segment Crack detection (648 images) achieves 12.4% improvement, Construction PPE (1K images) gains 13.7%, and KITTI (7K images) shows 88.6% improvement, while maintaining real-time inference (30-47 FPS). Systematic ablation across five YOLO scales and nine DINOv3 variants reveals that Medium-scale architectures achieve optimal performance with DualP0P3 integration (55.77% mAP@0.5), while Small-scale requires Triple Integration (53.63%). The 2-4x inference overhead (21-33ms versus 8-16ms baseline) remains acceptable for field deployment on NVIDIA RTX 5090. DINO-YOLO establishes state-of-the-art performance for civil engineering datasets (<10K images) while preserving computational efficiency, providing practical solutions for construction safety monitoring and infrastructure inspection in data-constrained environments.
format Preprint
id arxiv_https___arxiv_org_abs_2510_25140
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DINO-YOLO: Self-Supervised Pre-training for Data-Efficient Object Detection in Civil Engineering Applications
P, Malaisree
S, Youwai
T, Kitkobsin
S, Janrungautai
D, Amorndechaphon
P, Rojanavasu
Computer Vision and Pattern Recognition
Artificial Intelligence
Object detection in civil engineering applications is constrained by limited annotated data in specialized domains. We introduce DINO-YOLO, a hybrid architecture combining YOLOv12 with DINOv3 self-supervised vision transformers for data-efficient detection. DINOv3 features are strategically integrated at two locations: input preprocessing (P0) and mid-backbone enhancement (P3). Experimental validation demonstrates substantial improvements: Tunnel Segment Crack detection (648 images) achieves 12.4% improvement, Construction PPE (1K images) gains 13.7%, and KITTI (7K images) shows 88.6% improvement, while maintaining real-time inference (30-47 FPS). Systematic ablation across five YOLO scales and nine DINOv3 variants reveals that Medium-scale architectures achieve optimal performance with DualP0P3 integration (55.77% mAP@0.5), while Small-scale requires Triple Integration (53.63%). The 2-4x inference overhead (21-33ms versus 8-16ms baseline) remains acceptable for field deployment on NVIDIA RTX 5090. DINO-YOLO establishes state-of-the-art performance for civil engineering datasets (<10K images) while preserving computational efficiency, providing practical solutions for construction safety monitoring and infrastructure inspection in data-constrained environments.
title DINO-YOLO: Self-Supervised Pre-training for Data-Efficient Object Detection in Civil Engineering Applications
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2510.25140