Despite the remarkable achievement of recent underwater image restoration techniques, the lack of labeled data has become a major hurdle for further progress. In this work, we propose a mean-teacher based Semi-supervised Underwater Image Restoration (Semi-UIR) framework to incorporate the unlabeled data into network training. However, the naive mean-teacher method suffers from two main problems: (1) The consistency loss used in training might become ineffective when the teacher's prediction is wrong. (2) Using L1 distance may cause the network to overfit wrong labels, resulting in confirmation bias. To address the above problems, we first introduce a reliable bank to store the "best-ever" outputs as pseudo ground truth. To assess the quality of outputs, we conduct an empirical analysis based on the monotonicity property to select the most trustworthy NR-IQA method. Besides, in view of the confirmation bias problem, we incorporate contrastive regularization to prevent the overfitting on wrong labels. Experimental results on both full-reference and non-reference underwater benchmarks demonstrate that our algorithm has obvious improvement over SOTA methods quantitatively and qualitatively. Code has been released at https://github.com/Huang-ShiRui/Semi-UIR.

翻译：尽管近期水下图像恢复技术取得了显著成就，但标注数据的匮乏已成为制约其进一步发展的主要障碍。本文提出一种基于均值教师模型的水下半监督图像恢复框架（Semi-UIR），将无标注数据融入网络训练。然而，朴素均值教师方法存在两个主要问题：（1）当教师模型预测错误时，训练中使用的损失函数可能失效；（2）采用L1距离可能导致网络过度拟合错误标签，引发确认偏差。为解决上述问题，我们首先引入可靠库存储历史最优输出作为伪真值。为评估输出质量，我们基于单调性属性进行实证分析，筛选最可信的无参考图像质量评估方法。此外，针对确认偏差问题，我们引入对比正则化机制以防止对错误标签的过拟合。在全参考与无参考水下基准测试上的实验结果表明，本算法在定量和定性指标上均显著优于现有最优方法。代码已开源至https://github.com/Huang-ShiRui/Semi-UIR。