论文标题
测试时间适应真实图像通过元转移学习
Test-time Adaptation for Real Image Denoising via Meta-transfer Learning
论文作者
论文摘要
近年来，已经对真实图像deno的任务进行了大量研究。但是，通过创建更好的网络体系结构来改善真实图像的努力。我们探索了一个不同的方向，我们建议通过更好的学习策略来改善真实图像降级性能，该策略可以在多任务网络上进行测试时间适应。学习策略是两个阶段，第一阶段使用元辅助学习预先培训网络以获得更好的荟萃启动。同时，我们使用元学习来进行微调（元转移学习）作为培训的第二阶段，以实现对真实嘈杂图像的测试时间适应。为了利用更好的学习策略，我们还提出了一个网络体系结构，具有自我监督的掩盖重建损失。实际嘈杂数据集的实验显示了所提出的方法的贡献，并表明该方法可以优于其他SOTA方法。
In recent years, a ton of research has been conducted on real image denoising tasks. However, the efforts are more focused on improving real image denoising through creating a better network architecture. We explore a different direction where we propose to improve real image denoising performance through a better learning strategy that can enable test-time adaptation on the multi-task network. The learning strategy is two stages where the first stage pre-train the network using meta-auxiliary learning to get better meta-initialization. Meanwhile, we use meta-learning for fine-tuning (meta-transfer learning) the network as the second stage of our training to enable test-time adaptation on real noisy images. To exploit a better learning strategy, we also propose a network architecture with self-supervised masked reconstruction loss. Experiments on a real noisy dataset show the contribution of the proposed method and show that the proposed method can outperform other SOTA methods.
