IEEE Trans Pattern Anal Mach Intell. 2022 Dec;44(12):9222-9235. doi: 10.1109/TPAMI.2021.3125041. Epub 2022 Nov 7.
Neural networks that are based on the unfolding of iterative solvers as LISTA (Learned Iterative Soft Shrinkage), are widely used due to their accelerated performance. These networks, trained with a fixed dictionary, are inapplicable in varying model scenarios, as opposed to their flexible non-learned counterparts. We introduce, Ada-LISTA, an adaptive learned solver which receives as input both the signal and its corresponding dictionary, and learns a universal architecture to serve them all. This scheme allows solving sparse coding in linear rate, under varying models, including permutations and perturbations of the dictionary. We provide an extensive theoretical and numerical study, demonstrating the adaptation capabilities of our approach, and its application to the task of natural image inpainting.
基于迭代求解器展开的神经网络（如 LISTA（Learned Iterative Soft Shrinkage））由于其加速性能而被广泛使用。这些网络使用固定字典进行训练，在不同的模型场景中不适用，而其灵活的非学习对应物则适用。我们引入了 Ada-LISTA，这是一种自适应学习求解器，它接收信号及其对应的字典作为输入，并学习通用架构来为它们提供服务。这种方案允许在线性速率下解决稀疏编码问题，适用于各种模型，包括字典的置换和扰动。我们提供了广泛的理论和数值研究，展示了我们方法的适应能力及其在自然图像修复任务中的应用。
