论文标题
域适应性的相互学习：使用样品周期的自我验证图像去悬空网络
Mutual Learning for Domain Adaptation: Self-distillation Image Dehazing Network with Sample-cycle
论文作者
论文摘要
基于深度学习的方法已为图像飞机取得了重大成就。但是，大多数现有的飞行网络都集中在使用模拟的朦胧图像上的训练模型上，从而导致概括性能降解，因为域移动，将其应用于现实世界中的朦胧图像。在本文中，我们为域适应性提出了一个相互学习的除去框架。具体来说，我们首先设计了两个暹罗网络：合成领域中的一个教师网络和真正的域中的学生网络，然后通过利用EMA和联合损失来以相互学习的方式优化它们。此外，我们设计了一种基于密度增强（HDA）模块的样本周期策略，以引入学生网络提供的伪现实世界图像对，以进一步改善概括性能。关于合成和现实世界数据集的广泛实验表明，在主观和客观评估方面，建议的相互学习框架优于最先进的脱壳技术。
Deep learning-based methods have made significant achievements for image dehazing. However, most of existing dehazing networks are concentrated on training models using simulated hazy images, resulting in generalization performance degradation when applied on real-world hazy images because of domain shift. In this paper, we propose a mutual learning dehazing framework for domain adaption. Specifically, we first devise two siamese networks: a teacher network in the synthetic domain and a student network in the real domain, and then optimize them in a mutual learning manner by leveraging EMA and joint loss. Moreover, we design a sample-cycle strategy based on density augmentation (HDA) module to introduce pseudo real-world image pairs provided by the student network into training for further improving the generalization performance. Extensive experiments on both synthetic and real-world dataset demonstrate that the propose mutual learning framework outperforms state-of-the-art dehazing techniques in terms of subjective and objective evaluation.
