# DINO-YOLO: Self-Supervised Pre-training for Data-Efficient Object Detection in Civil Engineering Applications

Source: [DINO-YOLO: Self-Supervised Pre-training for Data-Efficient Object Detection in Civil Engineering Applications](<https://www.sota2.com/research/paper/6902f0dd3ef7ccd74e5e4090>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-11-04T05:03:20.568Z

Authors: Malaisree P, Youwai S, Kitkobsin T, Janrungautai S, Amorndechaphon D, Rojanavasu P

Published: 2025-10-29T03:40:40.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2510.25140>)

[PDF](<https://arxiv.org/pdf/2510.25140.pdf>)