Image deblurring is dedicated to restoring blurry images resulting from camera shake or target motion into high-quality sharp images. Recent work has made notable progress in image deblurring, but few studies have focused on the role of high-frequency information in this task. Hence, an efficient Edge-aware Laplacian Pyramid Network (ELPNet) is proposed for image deblurring. Specifically, we introduce a reversible Laplacian pyramid decomposition and reconstruction mechanism within the deblurring network, guiding the reconstruction of high-frequency information. Additionally, we present a novel Large-Kernel convolution Hybrid Attention Block (LKHAB) that leverages re-parameterization to effectively integrate channel-wise and spatial-invariant features with a larger receptive field. We also introduce an Edge-Aware Merge Block (EAMB) that combines Laplacian and Scharr operators with difference convolutions to create various learnable edge gradient convolutions. The EAMB can elegantly capture the edge information of features, and through re-parameterization, enables to merging of different edge gradient convolutions into a vanilla convolution during inference. Experimental results show that the proposed method achieves state-of-the-art performance with significantly reduced parameters and computation.

Multi-frame Super-Resolution (MFSR) aims to reconstruct a high-resolution (HR) image from a sequence of burst images, thereby overcoming the information scarcity limitations inherent in Single Image Super-Resolution (SISR). In this paper, we propose ECBANet, unlike most existing approaches, we employ an efficient and lightweight Pre-Alignment module to select sharp frames and align multiple frames, and we emphasize the complementarity between frames and introduce the Complementary Affinity Fusion (CAF) module. To better harness the complementarity of burst images in conjunction with CAF, we propose the Flexible Expansion Recursive Fusion (FlexERF) module, which finely and efficiently fuses features from arbitrary frames through its two sub-modules: the Recursive Fusion module and the Expansion Fusion module. Finally, we have conducted extensive experiments on different MFSR datasets, and the results show that our ECBANet surpasses existing state-of-the-art burst super-resolution methods.

In medical images, various types of lesions often manifest significant differences in their shape and texture. Accurate medical image segmentation demands deep learning models with robust capabilities in multi-scale and boundary feature learning. However, previous models still have limitations in addressing the above issues. The majority of medical image segmentation networks exclusively learn features in the spatial domain, disregarding the abundant global information in the frequency domain. This results in a bias towards low-frequency components, neglecting crucial high-frequency information. To address these problems, we introduce SF-UNet, a spatial-frequency dual-domain attention network. It comprises two main components: the Multi-scale Progressive Channel Attention (MPCA) block, which progressively extract multi-scale features across adjacent encoder layers, and the lightweight Frequency-Spatial Attention (FSA) block, with only 0.05M parameters, enabling concurrent learning of texture and boundary features from both spatial and frequency domains. We validate the effectiveness of the proposed SF-UNet on three public datasets. Experimental results show that compared to previous state-of-the-art medical image segmentation networks, SF-UNet achieves the best performance, and achieves up to 9.4% and 10.78% improvement in DSC and IOU. Codes will be released at https://github.com/nkicsl/SF-UNet.

Robustness to Byzantine attacks is a necessity for various distributed training scenarios. When the training reduces to the process of solving a minimization problem, Byzantine robustness is relatively well-understood. However, other problem formulations, such as min-max problems or, more generally, variational inequalities, arise in many modern machine learning and, in particular, distributed learning tasks. These problems significantly differ from the standard minimization ones and, therefore, require separate consideration. Nevertheless, only one work [Abidi et al., 2022] addresses this important question in the context of Byzantine robustness. Our work makes a further step in this direction by providing several (provably) Byzantine-robust methods for distributed variational inequality, thoroughly studying their theoretical convergence, removing the limitations of the previous work, and providing numerical comparisons supporting the theoretical findings.

Abstract Liver cancer poses a great threat to people's health. Accurate liver segmentation is crucial to the diagnosis of liver cancer. In recent years, great achievements have been made in liver segmentation using a series of improved networks developed based on U‐Net. U‐Net uses a skip connection splices the feature map in the encoder and decoder. However, this method ignores the difference between the two feature maps, which limits the ability of the network to extract liver structures of different sizes. This study proposes a new network structure, the pyramid convolutional attention fusion network (PCAF‐Net), for 2D liver segmentation. The PCAF mechanism was introduced to fuse the feature maps of different receptive field paths after attention mechanism processing to enhance the semantic expression ability of feature maps in skip connection and to improve the segmentation accuracy. The MICCAI 2017 LiTS dataset and CHAOS were used to validate the proposed method. The results of multi‐index evaluation showed that the segmentation performance of the proposed network was superior to those of other networks. PCAF‐Net achieved accurate liver segmentation, providing a reference for artificial intelligenceassisted clinical diagnosis of liver cancer.

To enhance the effectiveness of differential evolution (DE) algorithm, in recent years, a number of DE variants have been proposed by employing the idea of multiple strategies. Although these DE variants have been shown competitive performance, there still exists a problem for them that the strategy selection mechanism mainly relies on the historical search experience. Unfortunately, the historical search experience may be suitable for the problems with a flat fitness landscape, while not for the problems with a rugged fitness landscape. To alleviate the issue, in this work, an individual-dependent DE variant, called IPDE, is proposed by using the dual information guidance, including the fitness information and spatial information. In the IPDE, the idea of multiple strategies is used as well, but its most salient feature lies in that the strategy selection mechanism is based on the individual role rather than the historical search experience. To better identify the individual role, the fitness information and spatial information are used simultaneously, which can roughly estimate the evolutionary statuses of different individuals in the fitness landscape. To validate the effectiveness of IPDE, 52 benchmark functions are used in the experiments, and four well-established evolutionary algorithms are included in the performance comparison. The final results show that IPDE can achieve promising performance.