arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.11713cs.CV
收藏

NAS-DIP:使用神经架构搜索学习深度图像先验

NAS-DIP: Learning Deep Image Prior with Neural Architecture Search

Virginia Tech(弗吉尼亚理工大学)

Yun-Chun Chen, Chen Gao, Esther Robb, Jia-Bin Huang

摘要:

最近的工作表明,深度卷积神经网络的结构可以用作解决各种逆图像复原任务的结构化图像先验。而不是使用手工设计的架构,我们建议寻找神经架构,捕捉更强的图像先验。基于通用的U-Net架构,我们的核心贡献在于为(1)上采样单元和(2)跨尺度残差连接模式设计新的搜索空间。我们通过利用现有的神经架构搜索算法(使用具有递归神经网络控制器的强化学习)来搜索改进的网络。我们通过各种各样的应用程序,包括图像复原,去雾,图像到图像的翻译,和矩阵分解验证我们的方法的有效性。大量的实验结果表明,我们的算法表现良好,对国家的最先进的无学习的方法,并达到竞争力的性能与现有的基于学习的方法在某些情况下。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑