SEA-PACE: Semi-Supervised Underwater Image Enhancement via Gaussian Process–Assisted Self-Paced Learning
Jingyang Wang, Hengyue Bi, Jingchao Cao, Feng Gao, Junyu Dong
Abstract
The scarcity of paired data severely limits the performance and generalization of learning-based underwater image enhancement (UIE) methods. This challenge is particularly prominent in scenes with complex degradations. Semi-supervised learning has emerged as a promising solution by enabling the utilization of large-scale unlabeled data. However, its effectiveness is limited by the use of static, model-agnostic metrics for pseudo-label reliability assessment. To address this, we propose SEA-PACE, a novel semi-supervised framework that integrates model-aware uncertainty modeling and self-paced consistency learning to fully exploit unlabeled data for UIE. Specifically, we design a Model-Aware Reliability Estimator (MARE) that quantifies the uncertainty of the teacher model
BibTeX
@inproceedings{aaai2026_seapacesemisuper,
title = {SEA-PACE: Semi-Supervised Underwater Image Enhancement via Gaussian Process–Assisted Self-Paced Learning},
author = {Jingyang Wang and Hengyue Bi and Jingchao Cao and Feng Gao and Junyu Dong},
booktitle = {AAAI 2026},
year = {2026}
}