Search

The existing remote sensing (RS) image dehazing methods based on deep learning have sought help from the convolutional frameworks. Nevertheless, the inherent limitations of convolution, i.e., local receptive fields and independent input elements, curtail the network from learning the long-range dependencies and nonuniform distributions. To this end, we design an effective RS image dehazing Transformer architecture, denoted as RSDformer. First, given the irregular shapes and nonuniform distributions of haze in RS images, capturing both local and non-local features is crucial for RS image dehazing models. Hence, we propose a detail-compensated transposed attention (DCTA) to extract the global and local dependencies (LDs) across channels. Second, to enhance the ability to learn degraded features and better guide the restoration process, we develop a dual-frequency adaptive block (DFAB) with dynamic filters. Finally, a dynamic gated fusion block (DGFB) is designed to achieve fuse and exchange features across different scales effectively. In this way, the model exhibits robust capabilities to capture dependencies from both global and local areas, resulting in improving image content recovery. Extensive experiments prove that the proposed method obtains more appealing performances against other competitive methods. [ABSTRACT FROM AUTHOR]

In massive multi-input multi-output (MIMO) systems, it is necessary for user equipment (UE) to transmit downlink channel state information (CSI) back to the base station (BS). As the number of antennas increases, the feedback overhead of CSI consumes a significant amount of uplink bandwidth resources. To minimize the bandwidth overhead, we propose an efficient parallel attention transformer, called EPAformer, a lightweight network that utilizes the transformer architecture and efficient parallel self-attention (EPSA) for CSI feedback tasks. The EPSA expands the attention area of each token within the transformer block effectively by dividing multiple heads into parallel groups and conducting self-attention in horizontal and vertical stripes. The proposed EPSA achieves better feature compression and reconstruction. The simulation results display that the EPAformer surpasses previous deep learning-based approaches in terms of reconstruction performance and complexity. [ABSTRACT FROM AUTHOR]

In recent years, many deep learning-based methods have been utilized for the feedback of Channel State Information (CSI) in massive MIMO systems. The Transformer-based networks leverage global self-attention mechanisms that can effectively capture remote correlations between antennas, while Convolutional Neural Networks (CNNs) excel in acquiring local information. To balance the advantages of both, this paper proposes an Efficient Feature Aggregation Network called EFANet, which hybrid CNNs and Transformer. Specifically, we propose a Refined Window Multi-head Self-Attention (RW-MSA) through hybrid Convolutional Embedding Unit (CEU) and Window Multi-head Self-Attention (W-MSA) to reduce information loss between windows and achieve efficient feature aggregation. Additionally, we develop a Local Enhanced Feedforward Network (LEFN) to further integrate local information in the CSI matrix and model detailed features of different regions. Finally, the Compensation Unit (CU) is designed to further compensate for global-local features in the CSI matrix. Through the above design, the global and local features are fully interactive to reduce information loss. Numerous experiments have shown that the proposed method achieves better CSI reconstruction performance while reducing computational complexity. [ABSTRACT FROM AUTHOR]

Recently, Transformer-based architecture has been introduced into single image deraining tasks due to its advantage in modeling non-local information. However, existing approaches typically utilize self-attention along single spatial or channel dimension. They neglect feature fusion in different dimensions to explore contextual information fully, which limits the effective receptive field of the network and makes it challenging to learn image degradation relationships. To fully explore potential correlations between different dimensions of degraded images, we develop a D ual-branch C ollaborative Trans former , called DCformer. To be specific, we employ parallel multi-head self-attention (PMSA) as the core block to extract long-range contextual relationships across spatial and channel dimensions. Additionally, a local perception block (LPB) is introduced to provide the ability of local information acquisition in the network, which is complementary to the global modeling ability of the parallel hybrid self-attention mechanism. Finally, we design a feature interaction block (FIB) to further enhance the interaction of features at different resolutions. Extensive experiments on benchmark datasets demonstrate the effectiveness of our proposed method. [ABSTRACT FROM AUTHOR]