# Supervised Virtual-to-Real Domain Adaptation for Object Detection Task using YOLO

## TL;DR

This paper explores supervised domain adaptation from virtual to real data for object detection using YOLOv4, achieving high accuracy with limited real data by fine-tuning on backbone weights.

## Contribution

It introduces a domain adaptation approach using virtual datasets and fine-tuning YOLOv4's backbone to improve real-world object detection performance.

## Key findings

- Achieved 74.457% mAP with limited real data
- Fine-tuning backbone weights enhances domain adaptation
- Virtual datasets can effectively supplement real data

## Abstract

Deep neural network shows excellent use in a lot of real-world tasks. One of the deep learning tasks is object detection. Well-annotated datasets will affect deep neural network accuracy. More data learned by deep neural networks will make the model more accurate. However, a well-annotated dataset is hard to find, especially in a specific domain. To overcome this, computer-generated data or virtual datasets are used. Researchers could generate many images with specific use cases also with its annotation. Research studies showed that virtual datasets could be used for object detection tasks. Nevertheless, with the usage of the virtual dataset, the model must adapt to real datasets, or the model must have domain adaptability features. We explored the domain adaptation inside the object detection model using a virtual dataset to overcome a few well-annotated datasets. We use VW-PPE dataset, using 5000 and 10000 virtual data and 220 real data. For model architecture, we used YOLOv4 using CSPDarknet53 as the backbone and PAN as the neck. The domain adaptation technique with fine-tuning only on backbone weight achieved a mean average precision of 74.457%.