Training Implicit Networks for Image Deblurring using Jacobian-Free Backpropagation
Recent efforts in applying implicit networks to solve inverse problems in imaging have achieved competitive or even superior results when compared to feedforward networks. These implicit networks only require constant memory during backpropagation, regardless of the number of layers. However, they are not necessarily easy to train. Gradient calculations are computationally expensive because they require backpropagating through a fixed point. In particular, this process requires solving a large linear system whose size is determined by the number of features in the fixed point iteration. This paper explores a recently proposed method, Jacobian-free Backpropagation (JFB), a backpropagation scheme that circumvents such calculation, in the context of image deblurring problems. Our results show that JFB is comparable against fine-tuned optimization schemes, state-of-the-art (SOTA) feedforward networks, and existing implicit networks at a reduced computational cost.
Code (0)
등록된 구현이 없습니다.
Tasks
DeblurringImage DeblurringSimilar Papers 제목 키워드 기반
JFB: Jacobian-Free Backpropagation for Implicit Networks
A promising trend in deep learning replaces traditional feedforward networks with implicit networks. Unlike traditional networks, implicit networks solve a fixed point equation to compute inferences. Solving for the fixe…
ID-Blau: Image Deblurring by Implicit Diffusion-based reBLurring AUgmentation
Image deblurring aims to remove undesired blurs from an image captured in a dynamic scene. Much research has been dedicated to improving deblurring performance through model architectural designs. However, there is littl…
Data AugmentationDeblurringImage DeblurringSHINE: SHaring the INverse Estimate from the forward pass for bi-level optimization and implicit models
In recent years, implicit deep learning has emerged as a method to increase the effective depth of deep neural networks. While their training is memory-efficient, they are still significantly slower to train than their e…
Hyperparameter OptimizationOn the Convergence of Jacobian-Free Backpropagation for Optimal Control Problems with Implicit Hamiltonians
Optimal feedback control with implicit Hamiltonians poses a fundamental challenge for learning-based value function methods due to the absence of closed-form optimal control laws. Recent work~\cite{gelphman2025end} intro…
BluRef: Unsupervised Image Deblurring with Dense-Matching References
This paper introduces a novel unsupervised approach for image deblurring that utilizes a simple process for training data collection, thereby enhancing the applicability and effectiveness of deblurring methods. Our techn…
Image Deblurring