paper-with-me

Papers

Training Implicit Networks for Image Deblurring using Jacobian-Free Backpropagation

2024-02-03 · Linghai Liu, Shuaicheng Tong, Lisa Zhao

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.

📄 PDF Abstract BibTeX arXiv:2402.02065

Code (0)

등록된 구현이 없습니다.

Tasks

DeblurringImage Deblurring

Similar Papers 제목 키워드 기반

JFB: Jacobian-Free Backpropagation for Implicit Networks

2021-03-23 · Samy Wu Fung, Howard Heaton, Qiuwei Li, Daniel Mckenzie 외

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

2023-12-18 · CVPR 2024 1 · Jia-Hao Wu, Fu-Jen Tsai, Yan-Tsung Peng, Chung-Chi Tsai 외

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 Deblurring

SHINE: SHaring the INverse Estimate from the forward pass for bi-level optimization and implicit models

2021-06-01 · ICLR 2022 4 · Zaccharie Ramzi, Florian Mannel, Shaojie Bai, Jean-Luc Starck 외

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 Optimization

On the Convergence of Jacobian-Free Backpropagation for Optimal Control Problems with Implicit Hamiltonians

2026-01-31 · Eric Gelphman, Deepanshu Verma, Nicole Tianjiao Yang, Stanley Osher 외 arxiv

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

2026-03-15 · Bang-Dang Pham, Anh Tran, Cuong Pham, Minh Hoai arxiv

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