论文标题
一个灵活的框架，用于设计具有自适应平滑和游戏编码的可训练的先验
A Flexible Framework for Designing Trainable Priors with Adaptive Smoothing and Game Encoding
论文作者
论文摘要
我们介绍了一个通用框架，用于设计和训练神经网络层，其正向通行证可以解释为解决非平滑凸优化问题，并且其架构是从优化算法中得出的。我们专注于凸游戏，由图形节点代表并通过正规化函数进行交互的本地代理解决。这种方法吸引了解决成像问题，因为它允许在可训练的端到头的深层模型中使用经典的图像先验。本演讲中使用的先验包括总变异，拉普拉斯正则化，双边滤波，稀疏的词典编码以及非本地自我相似性的变体。我们的模型完全可以解释，并且参数和数据有效。我们的实验证明了它们对从图像denoising和fmri的压缩感应到密集的立体声匹配等各种任务的有效性。
We introduce a general framework for designing and training neural network layers whose forward passes can be interpreted as solving non-smooth convex optimization problems, and whose architectures are derived from an optimization algorithm. We focus on convex games, solved by local agents represented by the nodes of a graph and interacting through regularization functions. This approach is appealing for solving imaging problems, as it allows the use of classical image priors within deep models that are trainable end to end. The priors used in this presentation include variants of total variation, Laplacian regularization, bilateral filtering, sparse coding on learned dictionaries, and non-local self similarities. Our models are fully interpretable as well as parameter and data efficient. Our experiments demonstrate their effectiveness on a large diversity of tasks ranging from image denoising and compressed sensing for fMRI to dense stereo matching.
