International Conference on Computer and Knowledge Engineering

Home / 14th International Conference on Computer and Knowledge Engineering

Bridging the Synthetic-to-Real Gap (BSRG): Creating Simulated Datasets for Domain Adaptation to Enhance Vehicle Detection

Authors :

Behnaz Sadeghigol¹ Mohammad Ali Keyvanrad²

1- Faculty of Electrical & Computer Engineering Malek Ashtar University of Technology 2- Faculty of Electrical & Computer Engineering Malek Ashtar University of Technology

Keywords :

Synthetic dataset،Unreal Engine،Object detection،Domain adaptation،Transfer learning،JLTV dataset

Abstract :

Deep neural network based military vehicle detectors pose particular challenges due to the scarcity of relevant images and limited access to vehicles in this domain. Moreover, Real-world data often poses significant challenges, including privacy, availability, and bias. To mitigate these challenges, synthetic datasets can be leveraged. This article explores the efficacy of synthetic datasets in training state-of-the-art object detection models, specifically focusing on the Joint Light Tactical Vehicle (JLTV). Using the powerful Unreal Engine, which can create highly realistic scenes, we generated a comprehensive synthetic dataset designed to simulate real-world conditions and enhance the training process for various detection algorithms. In this study, we evaluate two distinct models for object recognition: an enhanced domain matching approach utilizing the Masked Image Consistency (MIC) framework and an unsupervised domain matching approach employing confidence-based mixing (ConfMix). The MIC model achieved a mean Average Precision (mAP) at 50% of 47% on real-world data, while the ConfMix model attained a mAP@50 of 55%. These results underscore the pivotal role of synthetic data in advancing object recognition technologies. They also highlight potential research directions for improving synthetic dataset generation and enhancing model performance in practical applications. Examples of this dataset can be accessed at: https://github.com/behnaz-sadeghigol/JLTV_dataset.

Papers List

List of archived papers

A Cost-Sensitive Genetic Algorithm for Customer Segmentation in Auto Insurances

Alireza Khajenoori - Mohammad Saniee Abadeh - Mohsen Mohammadzadeh

Improvement of CluStream Algorithm Using Sliding Window for the Clustering of Data Streams

Sahar Ahsani - Morteza Yousef Sanati - Muharram Mansoorizadeh

Uncertainty-Aware Deep Ensembles for Confident Customer Churn Prediction with Rejection Option

Fatemeh Moradi - Mehran Tarif - Mohammadhossein Homaei

LightFedSelect: A Lightweight Framework for Byzantine-Robust Federated Learning

Seyed Saeed Razavi - Seyed Arsalan Vasegh Rahim Parvar - Soroosh Dadashi Pakdeh - Mohammad Matin Rezaeifard - Morteza Mollaie Chafi - Reza Ebrahimi Atani

Segmentation of Hard Exudates in Retinal Fundus Images Using BCDU-Net

Nafise Ameri - Nasser Shoeibi - Mojtaba Abrishami

Vision-Based Obstacle Avoidance in Drone Navigation using Deep Reinforcement Learning

Pooyan Rahmanzadeh Gervi - Ahad Harati - Sayed Kamaledin Ghiasi-Shirazi

U-Net-based Hippocampus Segmentation Models: Advancements and Challenges

Laya Mahmoudi - Majid Abbasi - Abolfazl Kanani

Sports News Summarization Using Ensebmle Learning

Moein Sartakhti.salimi@gmail.com - Mohammad Javad Maleki Kahaki - Ahmad Yoosofan - Seyyed Vahid Moravvej

FAHP-OF: A New Method for Load Balancing in RPL-based Internet of Things (IoT)

Mohammad Koosha - Behnam Farzaneh - Emad Alizadeh - Shahin Farzaneh

Stock market prediction using multi-objective optimization

Mahshid Zolfaghari - Hamid Fadishei - Mohsen Tajgardan - Reza Khoshkangini