Generative adversarial networks in object detection: A systematic literature review

The intersection of Generative Adversarial Networks (GANs) and object detection represents one of the most promising developments in modern computer vision, offering innovative solutions to longstanding challenges in visual recognition systems. This review presents a systematic analysis of how GANs...

Full description

Bibliographic Details
Main Authors: Anis Farihan, Mat Raffei, Sinung, Suakanto, Faqih, Hamami, Mohd Arfian, Ismail, Ernawan, Ferda
Format: Article
Language:English
Published: Informatics Department, Faculty of Science and Technology, UIN Sunan Gunung Djati Bandung 2025
Subjects:
Online Access:https://umpir.ump.edu.my/id/eprint/45090/
_version_ 1848827340682952704
author Anis Farihan, Mat Raffei
Sinung, Suakanto
Faqih, Hamami
Mohd Arfian, Ismail
Ernawan, Ferda
author_facet Anis Farihan, Mat Raffei
Sinung, Suakanto
Faqih, Hamami
Mohd Arfian, Ismail
Ernawan, Ferda
author_sort Anis Farihan, Mat Raffei
building UMP Institutional Repository
collection Online Access
description The intersection of Generative Adversarial Networks (GANs) and object detection represents one of the most promising developments in modern computer vision, offering innovative solutions to longstanding challenges in visual recognition systems. This review presents a systematic analysis of how GANs are transforming these challenges, examining their applications from 2020 to 2025. The paper investigates three primary domains where GANs have demonstrated remarkable potential: data augmentation for addressing data scarcity, occlusion handling techniques designed to manage visually obstructed objects, and enhancement methods specifically focused on improving small object detection performance. Analysis reveals significant performance improvements resulting from these GAN applications: data augmentation methods consistently boost detection metrics such as mAP and F1-score on scarce datasets, occlusion handling techniques successfully reconstruct hidden features with high PSNR and SSIM values, and small object detection techniques increase detection accuracy by up to 10% Average Precision in some studies. Collectively, these findings demonstrate how GANs, integrated with modern detectors, are greatly advancing object detection capabilities. Despite this progress, persistent challenges including computational cost and training stability remain. By critically analyzing these advancements and limitations, this paper provides crucial insights into the current state and potential future developments of GAN-based object detection systems.
first_indexed 2025-11-15T03:59:10Z
format Article
id ump-45090
institution Universiti Malaysia Pahang
institution_category Local University
language English
last_indexed 2025-11-15T03:59:10Z
publishDate 2025
publisher Informatics Department, Faculty of Science and Technology, UIN Sunan Gunung Djati Bandung
recordtype eprints
repository_type Digital Repository
spelling ump-450902025-08-05T01:35:08Z https://umpir.ump.edu.my/id/eprint/45090/ Generative adversarial networks in object detection: A systematic literature review Anis Farihan, Mat Raffei Sinung, Suakanto Faqih, Hamami Mohd Arfian, Ismail Ernawan, Ferda QA75 Electronic computers. Computer science T Technology (General) The intersection of Generative Adversarial Networks (GANs) and object detection represents one of the most promising developments in modern computer vision, offering innovative solutions to longstanding challenges in visual recognition systems. This review presents a systematic analysis of how GANs are transforming these challenges, examining their applications from 2020 to 2025. The paper investigates three primary domains where GANs have demonstrated remarkable potential: data augmentation for addressing data scarcity, occlusion handling techniques designed to manage visually obstructed objects, and enhancement methods specifically focused on improving small object detection performance. Analysis reveals significant performance improvements resulting from these GAN applications: data augmentation methods consistently boost detection metrics such as mAP and F1-score on scarce datasets, occlusion handling techniques successfully reconstruct hidden features with high PSNR and SSIM values, and small object detection techniques increase detection accuracy by up to 10% Average Precision in some studies. Collectively, these findings demonstrate how GANs, integrated with modern detectors, are greatly advancing object detection capabilities. Despite this progress, persistent challenges including computational cost and training stability remain. By critically analyzing these advancements and limitations, this paper provides crucial insights into the current state and potential future developments of GAN-based object detection systems. Informatics Department, Faculty of Science and Technology, UIN Sunan Gunung Djati Bandung 2025-06-05 Article PeerReviewed pdf en cc_by_nd_4 https://umpir.ump.edu.my/id/eprint/45090/1/Sustainable%20construction_Public%20involvement%20in%20monitoring%20EMP%20implementation.pdf Anis Farihan, Mat Raffei and Sinung, Suakanto and Faqih, Hamami and Mohd Arfian, Ismail and Ernawan, Ferda (2025) Generative adversarial networks in object detection: A systematic literature review. Jurnal Online Informatika, 10 (1). pp. 205-215. ISSN 2527-9165. (Published) https://doi.org/10.15575/join.v10i1.1576 https://doi.org/10.15575/join.v10i1.1576 https://doi.org/10.15575/join.v10i1.1576
spellingShingle QA75 Electronic computers. Computer science
T Technology (General)
Anis Farihan, Mat Raffei
Sinung, Suakanto
Faqih, Hamami
Mohd Arfian, Ismail
Ernawan, Ferda
Generative adversarial networks in object detection: A systematic literature review
title Generative adversarial networks in object detection: A systematic literature review
title_full Generative adversarial networks in object detection: A systematic literature review
title_fullStr Generative adversarial networks in object detection: A systematic literature review
title_full_unstemmed Generative adversarial networks in object detection: A systematic literature review
title_short Generative adversarial networks in object detection: A systematic literature review
title_sort generative adversarial networks in object detection: a systematic literature review
topic QA75 Electronic computers. Computer science
T Technology (General)
url https://umpir.ump.edu.my/id/eprint/45090/
https://umpir.ump.edu.my/id/eprint/45090/
https://umpir.ump.edu.my/id/eprint/45090/