2024/02/03 by Linghai Liu, Shuaicheng Tong, Liu, Linghai +3
Computer Science · Earth and Planetary Sciences · #Advanced Image Processing Techniques #FOS: Computer and information sciences #Image and Signal Denoising Methods #Machine Learning (cs.LG) #Seismic Imaging and Inversion Techniques
paper · pdf · doi:10.48550/arxiv.2402.02065
openalex publication_date 2024/02/03 · openalex created_date 2024/02/07 · openalex updated_date 2026/07/28
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.