Multi-Run Statistical Evaluation of Retinex-Net, SNR-Aware, and RetinexFormer for Nighttime Vehicle Re-Identification
-
Muhammad Rafif
*
Universitas Kristen Satya Wacana, Salatiga,
Indonesia
- Radius Tanone Universitas Kristen Satya Wacana, Salatiga, Indonesia (*) Corresponding Author
Abstract
Nighttime vehicle re-identification (Re-ID) is challenging because low illumination, sensor noise, and motion blur can obscure identity-related visual features in surveillance images. Comparative studies of low-light enhancement (LLE) as a preprocessing step for Re-ID often rely on a single training run, making it difficult to distinguish genuine method effects from training stochasticity. This study evaluates Retinex-Net, SNR-Aware, and RetinexFormer as LLE preprocessing methods for TransReID with a ViT-Base/16 backbone on a stratified nighttime subset of the DN-348 dataset. The subset contains 8,255 images from 150 training identities and 120 shared gallery/query identities, with nighttime degradation simulated using gamma darkening, Poisson-Gaussian noise, and Gaussian blur. Each scenario was trained using three independent random seeds, with performance summarized across runs using mean Average Precision (mAP) and Cumulative Matching Characteristic (CMC) at Rank-1, Rank-5, and Rank-10. Additional statistical validation was performed on a representative run using bootstrap confidence intervals and paired Wilcoxon signed-rank tests with Holm-Bonferroni correction. Image quality was additionally assessed using PSNR, SSIM, and LPIPS, while SIE and JPM were examined through a factorial ablation. RetinexFormer achieved the highest mean mAP of 48.90 ± 0.11%, followed by SNR-Aware at 48.69 ± 0.21% and the baseline at 48.51 ± 0.33%. However, neither RetinexFormer nor SNR-Aware showed a statistically significant improvement over the baseline, whereas Retinex-Net performed significantly worse. RetinexFormer also produced the best image-quality metrics, indicating that stronger visual restoration does not necessarily yield better downstream Re-ID. These findings demonstrate the importance of multi-run and statistically validated evaluation when assessing LLE methods for nighttime vehicle Re-ID. Given that none of the evaluated LLE methods yielded a statistically significant mAP improvement over the no-enhancement baseline, these results indicate that LLE should not be adopted by default as a preprocessing step for nighttime vehicle Re-ID and should only be deployed after scenario-specific multi-run statistical validation.
Downloads
References
A. Amiri, A. Kaya, and A. S. Kececi, “A Comprehensive Survey on Deep-Learning-Based Vehicle Re-Identification: Models, Data Sets, and Challenges,” arXiv preprint arXiv:2401.10643, 2024, doi: 10.48550/arXiv.2401.10643.
Y. Zhao, W. Ruan, H. Li, and M. Ye, “NightReID: A Large-Scale Nighttime Person Re-Identification Benchmark,” Proc. AAAI Conf. Artif. Intell., vol. 39, no. 10, pp. 10519–10527, 2025, doi: 10.1609/aaai.v39i10.33142.
X. Yuan, Y. He, and G. Hao, “Identity Hides in Darkness: Learning Feature Discovery Transformer for Nighttime Person Re-Identification,” Sensors, vol. 25, no. 3, Art. no. 862, 2025, doi: 10.3390/s25030862.
R. Tanone, “Conditional GAN Approach for Image to Image Translation on Potato Leaf,” International Journal of Information Technology and Business, vol. 6, no. 1, pp. 17–20, 2023, doi: 10.24246/ijiteb.612023.17-20.
C. Wei, W. Wang, W. Yang, and J. Liu, “Deep Retinex Decomposition for Low-Light Enhancement,” in British Machine Vision Conference (BMVC), 2018. doi: 10.48550/arXiv.1808.04560.
X. Xu, R. Wang, C.-W. Fu, and J. Jia, “SNR-Aware Low-Light Image Enhancement,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 17693–17703, 2022. doi: 10.1109/CVPR52688.2022.01719.
Y. Cai, H. Bian, J. Lin, H. Wang, R. Timofte, and Y. Zhang, “Retinexformer: One-Stage Retinex-Based Transformer for Low-Light Image Enhancement,” in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), pp. 12470–12479, 2023. doi: 10.48550/arXiv.2303.06705.
M. T. Rasheed, D. Shi, and H. Khan, “A Comprehensive Experiment-Based Review of Low-Light Image Enhancement Methods and Benchmarking Low-Light Image Quality Assessment,” Signal Process., vol. 204, Art. no. 108821, 2023, doi: 10.1016/j.sigpro.2022.108821.
C. Guo, C. Li, J. Guo, C. C. Loy, J. Hou, S. Kwong, and R. Cong, “Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 1780–1789, 2020. doi: 10.48550/arXiv.2001.06826.
Y. Jiang, X. Gong, D. Liu, Y. Cheng, C. Fang, X. Shen, J. Yang, P. Zhou, and Z. Wang, “EnlightenGAN: Deep Light Enhancement Without Paired Supervision,” IEEE Trans. Image Process., vol. 30, pp. 2340–2349, 2021, doi: 10.1109/TIP.2021.3051462.
J. Liu, D. Xu, W. Yang, M. Fan, and H. Huang, “Benchmarking Low-Light Image Enhancement and Beyond,” Int. J. Comput. Vis., vol. 129, no. 4, pp. 1153–1184, 2021, doi: 10.1007/s11263-020-01418-8.
C. Li, C. Guo, L. Han, J. Jiang, M.-M. Cheng, J. Gu, and C. C. Loy, “Low-Light Image and Video Enhancement Using Deep Learning: A Survey,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 44, no. 12, pp. 9396–9416, 2022, doi: 10.1109/TPAMI.2021.3126387.
Z. Tian, P. Qu, J. Li, Y. Sun, G. Li, Z. Liang, and W. Zhang, “A Survey of Deep Learning-Based Low-Light Image Enhancement,” Sensors, vol. 23, no. 18, Art. no. 7763, 2023, doi: 10.3390/s23187763.
J. Guo, J. Ma, Á. F. García-Fernández, Y. Zhang, and H. Liang, “A Survey on Image Enhancement for Low-Light Images,” Heliyon, vol. 9, no. 4, Art. no. e14558, 2023, doi: 10.1016/j.heliyon.2023.e14558.
J. Ye, C. Qiu, and Z. Zhang, “A Survey on Learning-Based Low-Light Image and Video Enhancement,” Displays, vol. 81, Art. no. 102614, 2024, doi: 10.1016/j.displa.2023.102614.
M. T. Islam, I. Alam, S. S. Woo, S. Anwar, I. K. H. Lee, and K. Muhammad, “LoLI-Street: Benchmarking Low-Light Image Enhancement and Beyond,” in Proc. Asian Conf. Comput. Vis. (ACCV), pp. 1250–1267, 2024. doi: 10.1007/978-981-96-0917-8_20.
Z. Yu, Z. Huang, J. Pei, L. Tahsin, and D. Sun, “Semantic-Oriented Feature Coupling Transformer for Vehicle Re-Identification in Intelligent Transportation System,” IEEE Trans. Intell. Transp. Syst., vol. 25, no. 3, pp. 2803–2813, 2024, doi: 10.1109/TITS.2023.3257873.
X. Bouthillier et al., “Accounting for Variance in Machine Learning Benchmarks,” in Proc. Mach. Learn. Syst. (MLSys), vol. 3, pp. 747–769, 2021. doi: 10.48550/arXiv.2103.03098.
P. Henderson, R. Islam, P. Bachman, J. Pineau, D. Precup, and D. Meger, “Deep Reinforcement Learning That Matters,” in Proc. AAAI Conf. Artif. Intell., pp. 3207–3214, 2018. doi: 10.48550/arXiv.1709.06560.
M. Herrmann et al., “Position: Why We Must Rethink Empirical Research in Machine Learning,” in Proc. Int. Conf. Mach. Learn. (ICML), PMLR, vol. 235, pp. 18228–18247, 2024. doi: 10.48550/arXiv.2405.02200.
A. Hochlehnert, H. Bhatnagar, V. Udandarao, S. Albanie, A. Prabhu, and M. Bethge, “A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility,” in Proc. Conf. Language Modeling (COLM), 2025. doi: 10.48550/arXiv.2504.07086.
S. He, H. Luo, P. Wang, F. Wang, H. Li, and W. Jiang, “TransReID: Transformer-Based Object Re-Identification,” in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), pp. 14993–15002, 2021. doi: 10.1109/ICCV48922.2021.01474.
H. Li, J. Chen, A. Zheng, Y. Wu, and J. Luo, “Day-Night Cross-Domain Vehicle Re-Identification,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 12626–12635, 2024. doi: 10.1109/CVPR52733.2024.01200.
L. Zheng, L. Shen, L. Tian, S. Wang, J. Wang, and Q. Tian, “Scalable Person Re-Identification: A Benchmark,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), pp. 1116–1124, 2015. doi: 10.1109/ICCV.2015.133.
X. Liu, W. Liu, H. Ma, and H. Fu, “Large-Scale Vehicle Re-Identification in Urban Surveillance Videos,” in Proc. IEEE Int. Conf. Multimedia Expo (ICME), pp. 1–6, 2016. doi: 10.1109/ICME.2016.7553002.
A. Dosovitskiy et al., “An Image Is Worth 16x16 Words: Transformers for Image Recognition at Scale,” in Proc. Int. Conf. Learn. Represent. (ICLR), 2021. doi: 10.48550/arXiv.2010.11929.
R. Zhang, P. Isola, A. A. Efros, E. Shechtman, and O. Wang, “The Unreasonable Effectiveness of Deep Features as a Perceptual Metric,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 586–595, 2018. doi: 10.1109/CVPR.2018.00068.
B. Efron and R. J. Tibshirani, An Introduction to the Bootstrap. New York, NY, USA: Chapman & Hall, 1993.
S. Holm, “A Simple Sequentially Rejective Multiple Test Procedure,” Scand. J. Stat., vol. 6, no. 2, pp. 65–70, 1979, doi: 10.2307/4615733.
H. Jiang, A. Luo, H. Fan, S. Han, and S. Liu, “Low-Light Image Enhancement With Wavelet-Based Diffusion Models,” ACM Trans. Graph., vol. 42, no. 6, Art. no. 238, 2023, doi: 10.1145/3618373.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Multi-Run Statistical Evaluation of Retinex-Net, SNR-Aware, and RetinexFormer for Nighttime Vehicle Re-Identification
Pages: 1022-1034
Copyright (c) 2026 Muhammad Rafif, Radius Tanone
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
