The deconvolution method (DM) is an effective tool for enhancing the impulsive features of rolling bearings. Deep network-based deconvolution methods transform complex numerical computations into network optimization,...
详细信息
Image blind deblurring is an ill-posed inverse problem in image processing. While deep learning approaches have demonstrated effectiveness, they often lack interpretability and require extensive data. To address these...
详细信息
Image blind deblurring is an ill-posed inverse problem in image processing. While deep learning approaches have demonstrated effectiveness, they often lack interpretability and require extensive data. To address these limitations, we propose a novel variational neural network based on algorithm unfolding. The model is solved using the half quadratic splitting (HQS) method and proximal gradient descent. For blur kernel estimation, we introduce an L0 regularizer to constrain the gradient information and use the fast fourier transform (FFT) to solve the iterative results, thereby improving accuracy. Image restoration is initiated with Gabor filters for the convolution kernel, and the activation function is approximated using a Gaussian radial basis function (RBF). Additionally, two attention mechanisms improve feature selection. The experimental results on various datasets demonstrate that our model outperforms state-of-the-art algorithm unfolding networks and other blind deblurring models. Our approach enhances interpretability and generalization while utilizing fewer data and parameters.
We study the problem of optimal power allocation in a single-hop ad hoc wireless network. In solving this problem, we propose a hybrid neural architecture inspired by the algorithmic unfolding of the iterative weighte...
详细信息
ISBN:
(纸本)9781728176055
We study the problem of optimal power allocation in a single-hop ad hoc wireless network. In solving this problem, we propose a hybrid neural architecture inspired by the algorithmic unfolding of the iterative weighted minimum mean squared error (WMMSE) method, that we denote as unfolded WMMSE (UWMMSE). The learnable weights within UWMMSE are parameterized using graph neural networks (GNNs), where the time-varying underlying graphs are given by the fading interference coefficients in the wireless network. These GNNs are trained through a gradient descent approach based on multiple instances of the power allocation problem. Once trained, UWMMSE achieves performance comparable to that of WMMSE while significantly reducing the computational complexity. This phenomenon is illustrated through numerical experiments along with the robustness and generalization to wireless networks of different densities and sizes.
Pansharpening aims at integrating a high-spatial-resolution panchromatic (PAN) image with a low-spatial-resolution multispectral (MS) image to generate a high-resolution MS (HRMS) image. It is a fundamental and signif...
详细信息
Pansharpening aims at integrating a high-spatial-resolution panchromatic (PAN) image with a low-spatial-resolution multispectral (MS) image to generate a high-resolution MS (HRMS) image. It is a fundamental and significant task in the field of remotely sensed images. Classic and convolutional neural network (CNN)-based algorithms have been developed, over the last decades, for pansharpening based on the spatial detail injection model. However, these algorithms have difficulties in extracting sufficient details or lack interpretability. In this letter, we present an algorithm unfolding pansharpening (AUP) for this task. In the proposed AUP, a two-step optimization model is first designed based on the spatial detail decomposition model. Then, the iteration processes induced by an optimization model are mapped to several detailed convolution (dc) blocks to solve the detail injection by a trainable neural network. Finally, the desired MS details are obtained in end-to-end manners through a decoder. The superiority of the proposed AUP is demonstrated by extensive experiments on datasets acquired by two different kinds of satellites. Each module of the AUP is interpretable, and its fused results are with fewer spectral and spatial distortions.
Multi-modal image fusion synthesizes information from multiple sources into a single image, facilitating downstream tasks such as semantic segmentation. Current approaches primarily focus on acquiring informative fusi...
详细信息
Multi-modal image fusion synthesizes information from multiple sources into a single image, facilitating downstream tasks such as semantic segmentation. Current approaches primarily focus on acquiring informative fusion images at the visual display stratum through intricate mappings. Although some approaches attempt to jointly optimize image fusion and downstream tasks, these efforts often lack direct guidance or interaction, serving only to assist with a predefined fusion loss. To address this, we propose an "unfolding Attribution Analysis Fusion network" (UAAFusion), using attribution analysis to tailor fused images more effectively for semantic segmentation, enhancing the interaction between the fusion and segmentation. Specifically, we utilize attribution analysis techniques to explore the contributions of semantic regions in the source images to task discrimination. At the same time, our fusion algorithm incorporates more beneficial features from the source images, thereby allowing the segmentation to guide the fusion process. Our method constructs a model-driven unfolding network that uses optimization objectives derived from attribution analysis, with an attribution fusion loss calculated from the current state of the segmentation network. We also develop a new pathway function for attribution analysis, specifically tailored to the fusion tasks in our unfolding network. An attribution attention mechanism is integrated at each network stage, allowing the fusion network to prioritize areas and pixels crucial for high-level recognition tasks. Additionally, to mitigate the information loss in traditional unfolding networks, a memory augmentation module is incorporated into our network to improve the information flow across various network layers. Extensive experiments demonstrate our method's superiority in image fusion and applicability to semantic segmentation. The code is available at https://***/HaowenBai/UAAFusion.
We develop an efficient and near-optimal solution for beamforming in multi-user multiple-input-multiple-output single-hop wireless ad-hoc interference networks. Inspired by the weighted minimum mean squared error (WMM...
详细信息
We develop an efficient and near-optimal solution for beamforming in multi-user multiple-input-multiple-output single-hop wireless ad-hoc interference networks. Inspired by the weighted minimum mean squared error (WMMSE) method, a classical approach to solving this problem, and the principle of algorithm unfolding, we present unfolded WMMSE (UWMMSE) for MU-MIMO. This method learns a parameterized functional transformation of key WMMSE variables using graph neural networks (GNNs), where the channel and interference components of a wireless network constitute the underlying graph. These GNNs are trained through gradient descent on a network utility metric using multiple instances of the beamforming problem. Comprehensive experimental analyses illustrate the superiority of UWMMSE over the classical WMMSE and state-of-the-art learning-based methods in terms of performance, generalizability, and robustness.
Solving linear inverse problems plays a crucial role in numerous applications. algorithm unfolding based, model-aware data-driven approaches have gained significant attention for effectively addressing these problems....
详细信息
Solving linear inverse problems plays a crucial role in numerous applications. algorithm unfolding based, model-aware data-driven approaches have gained significant attention for effectively addressing these problems. Learned iterative soft-thresholding algorithm (LISTA) and alternating direction method of multipliers compressive sensing network (ADMM-CSNet) are two widely used such approaches, based on ISTA and ADMM algorithms, respectively. In this work, we study optimization guarantees, i.e., achieving near-zero training loss with the increase in the number of learning epochs, for finite-layer unfolded networks such as LISTA and ADMM-CSNet with smooth soft-thresholding in an over-parameterized (OP) regime. We achieve this by leveraging a modified version of the Polyak-& Lstrok;ojasiewicz, denoted PL*, condition. Satisfying the PL* condition within a specific region of the loss landscape ensures the existence of a global minimum and exponential convergence from initialization using gradient descent based methods. Hence, we provide conditions, in terms of the network width and the number of training samples, on these unfolded networks for the PL* condition to hold, by deriving the Hessian spectral norm. Additionally, we show that the threshold on the number of training samples increases with the increase in the network width. Furthermore, we compare the threshold on training samples of unfolded networks with that of a standard fully-connected feed-forward network (FFNN) with smooth soft-thresholding non-linearity. We prove that unfolded networks have a higher threshold value than FFNN. Consequently, one can expect a better expected error for unfolded networks than FFNN.
A recently proposed unified precoding and pilot design optimization (UPPiDO) framework offers a reduction in both training and feedback overhead of acquiring channel state information (CSI) and an enhancement in robus...
详细信息
A recently proposed unified precoding and pilot design optimization (UPPiDO) framework offers a reduction in both training and feedback overhead of acquiring channel state information (CSI) and an enhancement in robustness (to CSI uncertainties) at the expense of a more computationally demanding precoding optimization. To address this increased complexity, in this paper we first propose an unfolding-friendly iterative algorithm, which can efficiently address a family of non-convex and non-smooth problems. Then, we develop an efficient approach to unfold the iterative algorithm designed. Besides being applicable to important and typical iterative optimization algorithms, a pivotal advantage of the proposed unfolding approach is that the trainable parameters are scalars (rather than matrices). This, in turn, reduces the number of training samples required and makes it suitable for rapidly fluctuating wireless environments. We apply the algorithm unfolding (AU) techniques developed to our UPPiDO-based symbol-level precoding and block-level precoding. Our complexity analysis indicates that the computational complexity is scalable both with the numbers of served users and antennas. Our simulation results demonstrate that the number of outer iterations (or layers) required is about 1/3 of that of the original iterative algorithms.
Due to the cost and accuracy of current point cloud sampling equipment, the obtained point color information is often corrupted by various noises. Existing point cloud denoising algorithms mainly focus on smoothness p...
详细信息
ISBN:
(纸本)9789819785070;9789819785087
Due to the cost and accuracy of current point cloud sampling equipment, the obtained point color information is often corrupted by various noises. Existing point cloud denoising algorithms mainly focus on smoothness priors and convex optimization. Their performances highly depend on model parameters whose values are determined manually and fixed throughout the iterations. In this paper, we propose to unfold gradient graph regularization with deep neural networks for point cloud color denoising. It improves the robustness of the model for denoising in different kinds of datasets and across domains. Specifically, our approach first uses a point cloud extraction network to obtain effective features for gradient computation. Then, we construct a gradient graph Laplacian regularization (GGLR) as signal smoothness prior to point cloud restoration. Finally, we introduce shallow neural networks for model parameter estimation to unfold GGLR. The proposed point cloud denoising framework is fully differentiable and can be trained end-to-end. Experiments show that the proposed algorithm unfolding outperforms several existing point cloud color denoising techniques.
Photon-limited deblurring is a complex and demanding problem encountered in various applications where low-light conditions prevail. The scarcity of photons in such situations leads to the introduction of shot noise, ...
详细信息
ISBN:
(纸本)9798350350463;9798350350456
Photon-limited deblurring is a complex and demanding problem encountered in various applications where low-light conditions prevail. The scarcity of photons in such situations leads to the introduction of shot noise, resulting in a degradation of image quality. Solving this problem with Neural networks often involves constructing models empirically, making the behavior of the underlying architecture challenging to comprehend. A recent technique known as algorithm unrolling has enabled the connection of iterative algorithms with neural networks, where the Convolutional Neural Network (CNN) acts as a denoiser. This paper introduces a reduced parameter denoiser to enhance image quality and preserve finer details or avoid over-smoothing of the image during reconstruction. As a result, the unrolled model surpasses existing deblurring methods for improving image quality in low-light conditions. The proposed denoiser reduces the number of parameters by a factor of 3.84 and preserves the finer details while reconstructing. Our model improves computational efficiency and storage requirements compared to the state-of-the-art.
暂无评论