Generative Adversarial Networks In Object Detection: A Systematic Literature Review

Anis Farihan Mat Raffei; Sinung Suakanto; Faqih Hamami; Mohd Arfian Ismail; Ferda Ernawan

doi:10.15575/join.v10i1.1576

Authors

Anis Farihan Mat Raffei Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah, Pahang, Malaysia
Sinung Suakanto Department of Information Systems, Faculty of Industrial Engineering, Telkom University, Bandung, Indonesia
Faqih Hamami Department of Information Systems, Faculty of Industrial Engineering, Telkom University, Bandung, Indonesia
Mohd Arfian Ismail Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah, Pahang, Malaysia
Ferda Ernawan Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah, Pahang, Malaysia

DOI:

https://doi.org/10.15575/join.v10i1.1576

Keywords:

Computer Vision, GANs, Image Processing, Object Detection, Occlusion

Abstract

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.

References

[1] M. Ahmed, K. A. Hashmi, A. Pagani, M. Liwicki, D. Stricker, and M. Z. Afzal, “Survey and Performance Analysis of Deep Learning Based Object Detection in Challenging Environments,” Sensors, vol. 21, no. 15, p. 5116, Jul. 2021, doi: 10.3390/s21155116.

[2] S. S. A. Zaidi, M. S. Ansari, A. Aslam, N. Kanwal, M. Asghar, and B. Lee, “A survey of modern deep learning based object detection models,” Digit Signal Process, vol. 126, p. 103514, Jun. 2022, doi: 10.1016/j.dsp.2022.103514.

[3] C. Wang, G. Huang, Z. Huang, and W. He, “Conditional TransGAN‐Based Data Augmentation for PCB Electronic Component Inspection,” Comput Intell Neurosci, vol. 2023, no. 1, Jan. 2023, doi: 10.1155/2023/2024237.

[4] Y. Lu, D. Chen, E. Olaniyi, and Y. Huang, “Generative adversarial networks (GANs) for image augmentation in agriculture: A systematic review,” Comput Electron Agric, vol. 200, p. 107208, Sep. 2022, doi: 10.1016/j.compag.2022.107208.

[5] L. Jiao et al., “New Generation Deep Learning for Video Object Detection: A Survey,” IEEE Trans Neural Netw Learn Syst, vol. 33, no. 8, pp. 3195–3215, Aug. 2022, doi: 10.1109/TNNLS.2021.3053249.

[6] Y. Liu, P. Sun, N. Wergeles, and Y. Shang, “A survey and performance evaluation of deep learning methods for small object detection,” Expert Syst Appl, vol. 172, p. 114602, Jun. 2021, doi: 10.1016/j.eswa.2021.114602.

[7] K. Zhang, X. Yang, L. Xu, J. Thé, Z. Tan, and H. Yu, “Enhancing coal-gangue object detection using GAN-based data augmentation strategy with dual attention mechanism,” Energy, vol. 287, p. 129654, Jan. 2024, doi: 10.1016/j.energy.2023.129654.

[8] Fortune Business Insights, “Generative AI Market Size, Share, Growth | Forecast [2030].” Accessed: Mar. 01, 2025. [Online]. Available: https://www.fortunebusinessinsights.com/generative-ai-market-107837

[9] G. Yang, C. Song, Z. Yang, and S. Cui, “Bubble detection in photoresist with small samples based on GAN augmentations and modified YOLO,” Eng Appl Artif Intell, vol. 123, p. 106224, Aug. 2023, doi: 10.1016/j.engappai.2023.106224.

[10] B. Bosquet, D. Cores, L. Seidenari, V. M. Brea, M. Mucientes, and A. Del Bimbo, “A full data augmentation pipeline for small object detection based on generative adversarial networks,” Pattern Recognit, vol. 133, p. 108998, Jan. 2023, doi: 10.1016/j.patcog.2022.108998.

[11] W. Wei, Y. Cheng, J. He, and X. Zhu, “A review of small object detection based on deep learning,” Neural Comput Appl, vol. 36, no. 12, pp. 6283–6303, Apr. 2024, doi: 10.1007/s00521-024-09422-6.

[12] Z. Zou, K. Chen, Z. Shi, Y. Guo, and J. Ye, “Object Detection in 20 Years: A Survey,” Proceedings of the IEEE, vol. 111, no. 3, pp. 257–276, Mar. 2023, doi: 10.1109/JPROC.2023.3238524.

[13] R. Kaur and S. Singh, “A comprehensive review of object detection with deep learning,” Digit Signal Process, vol. 132, p. 103812, Jan. 2023, doi: 10.1016/j.dsp.2022.103812.

[14] G. Iglesias, E. Talavera, and A. Díaz-Álvarez, “A survey on GANs for computer vision: Recent research, analysis and taxonomy,” Comput Sci Rev, vol. 48, p. 100553, May 2023, doi: 10.1016/j.cosrev.2023.100553.

[15] S. Xu, M. Zhang, W. Song, H. Mei, Q. He, and A. Liotta, “A systematic review and analysis of deep learning-based underwater object detection,” Neurocomputing, vol. 527, pp. 204–232, Mar. 2023, doi: 10.1016/j.neucom.2023.01.056.

[16] K. Saleh, S. Szénási, and Z. Vámossy, “Generative Adversarial Network for Overcoming Occlusion in Images: A Survey,” Algorithms, vol. 16, no. 3, p. 175, Mar. 2023, doi: 10.3390/a16030175.

[17] A. Gupta, A. Anpalagan, L. Guan, and A. S. Khwaja, “Deep learning for object detection and scene perception in self-driving cars: Survey, challenges, and open issues,” Array, vol. 10, p. 100057, Jul. 2021, doi: 10.1016/j.array.2021.100057.

[18] K. Tong, Y. Wu, and F. Zhou, “Recent advances in small object detection based on deep learning: A review,” Image Vis Comput, vol. 97, p. 103910, May 2020, doi: 10.1016/j.imavis.2020.103910.

[19] C. Xu et al., “Scarcity-GAN: Scarce data augmentation for defect detection via generative adversarial nets,” Neurocomputing, vol. 566, p. 127061, Jan. 2024, doi: 10.1016/j.neucom.2023.127061.

[20] Y. Haruna, S. Qin, and M. J. M. Kiki, “An Improved Approach to Detection of Rice Leaf Disease with GAN-Based Data Augmentation Pipeline,” Applied Sciences, vol. 13, no. 3, p. 1346, Jan. 2023, doi: 10.3390/app13031346.

[21] A. Ayub and H. Kim, “GAN-Based Data Augmentation with Vehicle Color Changes to Train a Vehicle Detection CNN,” Electronics (Basel), vol. 13, no. 7, p. 1231, Mar. 2024, doi: 10.3390/electronics13071231.

[22] H. Taguchi, R. Matsumura, and H. Kitakaze, “The effectiveness of GAN-based synthetic-to-real domain adaptation methods in training a wood ear mushroom detection model,” Artif Life Robot, vol. 30, no. 2, pp. 310–316, May 2025, doi: 10.1007/s10015-024-00998-9.

[23] J. Cai, H. Han, J. Cui, J. Chen, L. Liu, and S. K. Zhou, “Semi-Supervised Natural Face De-Occlusion,” IEEE Transactions on Information Forensics and Security, vol. 16, pp. 1044–1057, 2021, doi: 10.1109/TIFS.2020.3023793.

[24] M. Cao et al., “Recognition of Occluded Goods under Prior Inference Based on Generative Adversarial Network,” Sensors, vol. 23, no. 6, p. 3355, Mar. 2023, doi: 10.3390/s23063355.

[25] M. Abuhussein, I. Almadani, A. L. Robinson, and M. Younis, “Enhancing Obscured Regions in Thermal Imaging: A Novel GAN-Based Approach for Efficient Occlusion Inpainting,” J (Basel), vol. 7, no. 3, pp. 218–235, Jun. 2024, doi: 10.3390/j7030013.

[26] C. Meng, W. Yang, Y. Bai, H. Li, H. Zhang, and M. Li, “Research of soil surface image occlusion removal and inpainting based on GAN used for estimation of farmland soil moisture content,” Comput Electron Agric, vol. 212, p. 108155, Sep. 2023, doi: 10.1016/j.compag.2023.108155.

[27] K. Sun, Q. Wen, and H. Zhou, “Ganster R-CNN: Occluded Object Detection Network Based on Generative Adversarial Nets and Faster R-CNN,” IEEE Access, vol. 10, pp. 105022–105030, 2022, doi: 10.1109/ACCESS.2022.3211394.

[28] F. Wu et al., “An Enhanced Cycle Generative Adversarial Network Approach for Nighttime Pineapple Detection of Automated Harvesting Robots,” Agronomy, vol. 14, no. 12, p. 3002, Dec. 2024, doi: 10.3390/agronomy14123002.

[29] S. M. A. Bashir and Y. Wang, “Small Object Detection in Remote Sensing Images with Residual Feature Aggregation-Based Super-Resolution and Object Detector Network,” Remote Sens (Basel), vol. 13, no. 9, p. 1854, May 2021, doi: 10.3390/rs13091854.

[30] H. Salaudeen and E. Çelebi, “Pothole Detection Using Image Enhancement GAN and Object Detection Network,” Electronics (Basel), vol. 11, no. 12, p. 1882, Jun. 2022, doi: 10.3390/electronics11121882.

[31] K. Ren, Y. Gao, M. Wan, G. Gu, and Q. Chen, “Infrared small target detection via region super resolution generative adversarial network,” Applied Intelligence, vol. 52, no. 10, pp. 11725–11737, Aug. 2022, doi: 10.1007/s10489-021-02955-6.

[32] J. Rabbi, N. Ray, M. Schubert, S. Chowdhury, and D. Chao, “Small-Object Detection in Remote Sensing Images with End-to-End Edge-Enhanced GAN and Object Detector Network,” Remote Sens (Basel), vol. 12, no. 9, p. 1432, May 2020, doi: 10.3390/rs12091432.