相关论文: Memory-Augmented Deep Unfolding Network for Compre…

Although low-light image enhancement has achieved great stride based on deep enhancement models, most of them mainly stress on enhancement performance via an elaborated black-box network and rarely explore the physical significance of…

The performance of single image super-resolution has achieved significant improvement by utilizing deep convolutional neural networks (CNNs). The features in deep CNN contain different types of information which make different contributions…

Deep learning and Convolutional Neural Networks (CNNs) have driven major transformations in diverse research areas. However, their limitations in handling low-frequency information present obstacles in certain tasks like interpreting global…

Neural Memory Networks (NMNs) have received increased attention in recent years compared to deep architectures that use a constrained memory. Despite their new appeal, the success of NMNs hinges on the ability of the gradient-based…

Recommendation systems play a vital role to keep users engaged with personalized content in modern online platforms. Deep learning has revolutionized many research fields and there is a recent surge of interest in applying it to…

Deep unfolding networks have gained increasing attention in the field of compressed sensing (CS) owing to their theoretical interpretability and superior reconstruction performance. However, most existing deep unfolding methods often face…

Approximate machine unlearning (AMU) enables models to `forget' specific training data through specialized fine-tuning on a retained (and forget) subset of training set. However, processing this large retained subset still dominates…

Neural networks excel in detecting regular patterns but are less successful in representing and manipulating complex data structures, possibly due to the lack of an external memory. This has led to the recent development of a new line of…

Dynamic magnetic resonance (MR) imaging has generated great research interest, as it can provide both spatial and temporal information for clinical diagnosis. However, slow imaging speed or long scanning time is still one of the challenges…

The resurgence of near-memory processing (NMP) with the advent of big data has shifted the computation paradigm from processor-centric to memory-centric computing. To meet the bandwidth and capacity demands of memory-centric computing, 3D…

Deep neural networks (DNNs) typically employ an end-to-end (E2E) training paradigm which presents several challenges, including high GPU memory consumption, inefficiency, and difficulties in model parallelization during training. Recent…

While deep neural networks (NN) significantly advance image compressed sensing (CS) by improving reconstruction quality, the necessity of training current CS NNs from scratch constrains their effectiveness and hampers rapid deployment.…

Recently, deep learning techniques have been extensively studied for pansharpening, which aims to generate a high resolution multispectral (HRMS) image by fusing a low resolution multispectral (LRMS) image with a high resolution…

Hyperspectral imaging is an essential imaging modality for a wide range of applications, especially in remote sensing, agriculture, and medicine. Inspired by existing hyperspectral cameras that are either slow, expensive, or bulky,…

Modern power systems with high penetration of inverter-based resources exhibit complex dynamic behaviors that challenge the scalability and generalizability of traditional stability assessment methods. This paper presents a dynamic…

Multimodal medical image fusion is a crucial task that combines complementary information from different imaging modalities into a unified representation, thereby enhancing diagnostic accuracy and treatment planning. While deep learning…

By integrating certain optimization solvers with deep neural networks, deep unfolding network (DUN) with good interpretability and high performance has attracted growing attention in compressive sensing (CS). However, existing DUNs often…

Purpose: To develop a deep learning method on a nonlinear manifold to explore the temporal redundancy of dynamic signals to reconstruct cardiac MRI data from highly undersampled measurements. Methods: Cardiac MR image reconstruction is…

Compressive sensing (CS) is an effective approach for fast Magnetic Resonance Imaging (MRI). It aims at reconstructing MR images from a small number of under-sampled data in k-space, and accelerating the data acquisition in MRI. To improve…

Very deep convolutional neural networks (CNNs) yield state of the art results on a wide variety of visual recognition problems. A number of state of the the art methods for image recognition are based on networks with well over 100 layers…