Optimization-Inspired Learning with Architecture Augmentations and Control Mechanisms for Low-Level Vision
From MaRDI portal
Publication:6355704
arXiv2012.05435MaRDI QIDQ6355704
Author name not available (Why is that?)
Publication date: 9 December 2020
Abstract: In recent years, building deep learning models from optimization perspectives has becoming a promising direction for solving low-level vision problems. The main idea of most existing approaches is to straightforwardly combine numerical iterations with manually designed network architectures to generate image propagations for specific kinds of optimization models. However, these heuristic learning models often lack mechanisms to control the propagation and rely on architecture engineering heavily. To mitigate the above issues, this paper proposes a unified optimization-inspired deep image propagation framework to aggregate Generative, Discriminative and Corrective (GDC for short) principles for a variety of low-level vision tasks. Specifically, we first formulate low-level vision tasks using a generic optimization objective and construct our fundamental propagative modules from three different viewpoints, i.e., the solution could be obtained/learned 1) in generative manner; 2) based on discriminative metric, and 3) with domain knowledge correction. By designing control mechanisms to guide image propagations, we then obtain convergence guarantees of GDC for both fully- and partially-defined optimization formulations. Furthermore, we introduce two architecture augmentation strategies (i.e., normalization and automatic search) to respectively enhance the propagation stability and task/data-adaption ability. Extensive experiments on different low-level vision applications demonstrate the effectiveness and flexibility of GDC.
Has companion code repository: https://github.com/LiuZhu-CV/GDC-OptimizationLearning
This page was built for publication: Optimization-Inspired Learning with Architecture Augmentations and Control Mechanisms for Low-Level Vision
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6355704)
