论文标题
NAS浸：在神经体系结构搜索中学习深层图像
NAS-DIP: Learning Deep Image Prior with Neural Architecture Search
论文作者
论文摘要
最近的工作表明，深层卷积神经网络的结构可以用作解决各种逆图恢复任务的结构化图像。我们建议不使用手工设计的体系结构，而是搜索捕获更强图像先验的神经体系结构。在通用的U-NET体系结构的基础上，我们的核心贡献在于设计新的搜索空间（1）UPPLAING REMPLING单元格和（2）跨尺度剩余连接的模式。我们通过利用现有的神经体系结构搜索算法（使用经常性神经网络控制器的增强学习）来搜索改进的网络。我们通过多种应用来验证方法的有效性，包括图像恢复，飞机，图像到图像翻译和矩阵分解。广泛的实验结果表明，我们的算法对无疑的无学习方法表现出色，并在某些情况下通过现有基于学习的方法达到竞争性能。
Recent work has shown that the structure of deep convolutional neural networks can be used as a structured image prior for solving various inverse image restoration tasks. Instead of using hand-designed architectures, we propose to search for neural architectures that capture stronger image priors. Building upon a generic U-Net architecture, our core contribution lies in designing new search spaces for (1) an upsampling cell and (2) a pattern of cross-scale residual connections. We search for an improved network by leveraging an existing neural architecture search algorithm (using reinforcement learning with a recurrent neural network controller). We validate the effectiveness of our method via a wide variety of applications, including image restoration, dehazing, image-to-image translation, and matrix factorization. Extensive experimental results show that our algorithm performs favorably against state-of-the-art learning-free approaches and reaches competitive performance with existing learning-based methods in some cases.
