UDAPA: A Lightweight Adapter for Robust Underwater Image Enhancement via Input‐Side Alignment
IET Image Processing · 2026-01 · 20 (1)
DOI: 10.1049/ipr2.70424 ↗Kurz gefasst
Fachartikel in der Zeitschrift IET Image Processing, online erschienen am 07.07.2026. Verfasst von Hui Zhang und 2 weiteren Autor:innen. Die Arbeit nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Underwater image enhancement (UIE) aims to improve the visual quality of low‐quality inputs. However, existing data‐driven methods often suffer performance degradation when deployed in unseen underwater environments due to domain shift. Although retraining or fine‐tuning for each target domain may alleviate this issue, such strategies increase deployment cost and are difficult to scale in practice. To address this problem, we propose UDAPA, a lightweight adapter framework for robust underwater image enhancement via input‐side alignment. Rather than modifying the pre‐trained backbone, UDAPA adapts degraded inputs toward a feature distribution that is more compatible with the frozen pre‐trained model. The proposed adapter consists of an environment perception module (EPM) and an adaptive pre‐conditioning module (APM). The EPM exploits physically meaningful cues to perceive degradation characteristics and provide spatial guidance, while the APM performs pixel‐wise adaptive modulation for colour correction and local visibility enhancement. In this way, the proposed adapter recalibrates out‐of‐distribution degraded inputs toward the feature‐statistics region preferred by the frozen backbone, thereby improving the robustness of the pre‐trained backbone under unseen conditions. Experimental results show that UDAPA consistently improves six representative UIE backbones, including CNN‐based, transformer‐based and diffusion‐based models, while introducing only marginal additional computational overhead. On out‐of‐distribution paired benchmarks, the proposed adapter achieves stable PSNR and SSIM improvements across different backbones, with representative gains reaching 1.86 dB/0.031 on EUVP and 2.17 dB/0.039 on UFO. These results demonstrate that UDAPA provides an effective and practical solution for enhancing the cross‐domain generalization of frozen pre‐trained UIE models. The code will be made publicly available at: https://github.com/zhangjuran/UDAPA .
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Zhang, H., Gao, Z., & Li, J. (2026). UDAPA: A Lightweight Adapter for Robust Underwater Image Enhancement via Input‐Side Alignment. IET Image Processing, 20(1). https://doi.org/10.1049/ipr2.70424
Vancouver
Zhang H, Gao Z, Li J. UDAPA: A Lightweight Adapter for Robust Underwater Image Enhancement via Input‐Side Alignment. IET Image Processing. 2026;20(1). doi:10.1049/ipr2.70424
BibTeX
@article{Zhang2026,
author = {Zhang, Hui and Gao, Zhaolong and Li, Jinjiang},
title = {UDAPA: A Lightweight Adapter for Robust Underwater Image Enhancement via Input‐Side Alignment},
journal = {IET Image Processing},
year = {2026},
volume = {20},
number = {1},
doi = {10.1049/ipr2.70424}
}
EUVIMED