In recent years, advancements in remote-sensing image super-resolution have achieved remarkable performance. However, many methods demand significant computational resources. This is problematic for edge devices with limited computational capabilities. To alleviate this problem, we propose an attention-based multi-level feature fusion network (AMFFN) to enhance the resolution of remote-sensing images. This proposed network integrates three efficient design strategies to provide a lightweight solution. Initially, we design the partial shallow residual block (PSRB) to replace the redundant convolution operation. The PSRB optimizes feature extraction via partial convolution and capitalizes on information across channels using pointwise convolution. Subsequently, integrating the PSRB, our dynamic feature distillation block (DFDB) leverages an information distillation mechanism to distill and capture only the crucial features securing a robust feature depiction. Conclusively, for superior feature fusion, we conceptualized an attention-based multi-level feature fusion (AMFF) mechanism. The attention intrinsic to AMFF weighs the significance of features from varied branches, assuring that the resulting output is comprehensive and discerning. We conduct thorough experimental validation on two datasets of remote-sensing images and measure network complexity by evaluating network parameters and multi-adds operations. The results show that our method effectively balances computational complexity and performance. In addition, we have expanded the application of AMFFN to the field of natural image super-resolution. Experimental results on five benchmark test datasets further confirm the effectiveness of our method.

Hyperspectral(HS) image classification has become an important research area. Although previous work on HS image classification has achieved impressive results, finding a proper balance between extracting spatial-spectral information and capturing band similarities remains a challenge. To address this problem, we designed some efficient modules and constructed a hybrid covariance attention and cross-layer fusion Transformer network (CACFTNet), which efficiently models the extraction of spatial-spectral information and band similarity. First, our approach combines local and global perspectives to process the desired feature information. We introduce the Dual Branch Feature Processing (DBFP) module, which can model the desired spatial-spectral information and band similarity. Secondly, we design the Dual Branch Feature Fusion (DBFF) module, which combines a Convolutional Neural Network (CNN) and a transformer to catch spatial-spectral information at different scales and fuse them effectively. To further process the features, we construct the Unparameterized Covariance Attention (UPCA) module, which utilizes the covariance matrix to capture the correlation between different spectral bands. This allows the network to concentrate on bands that are more useful for classification task. Additionally, we designed a hybrid activation function (HAF) that maps the channel values to specific ranges and emphasizes the extent to which the correlation varies between different bands. Finally, in order to incorporate important information from different layers, we propose the Cross-Layer Adaptive Attention Fusion (CAAF) module, which fully fuses information between layers and enriches the overall information representation. We evaluate our proposed model on three well-known public datasets and demonstrate its superiority over existing approaches.

Visible-infrared person re-identification (VI-ReID) is a challenging study aimed at retrieving the same person across cameras, time, and modalities. Existing methods usually employ dual-stream networks with integrated constraints, or compensate for modality information to reduce the significant modality discrepancies among heterogeneous images. However, the effectiveness of designed constraints is often limited due to substantial cross-modality differences, and methods that compensate for modality information may introduce noise and additional computational cost. In this paper, we propose a novel Multi-Stage Auxiliary Learning strategy called MSALNet. Specifically, in our approach, the training process is bifurcated into two stages: 1) training with auxiliary modality pairs obtained from grayscale histogram equalization, and 2) training with visible and infrared image pairs to gradually extract more discriminative modality-shared features. We propose the Heterogeneous Feature Compensation Learning (HFCL) module for information compensation and fusion between visible and infrared features, generating auxiliary branches to learn more cross-modality-related information. Additionally, we propose the Modality Similarity Reinforcement (MSR) module to improve the consistency of cross-modality feature representation by suppressing interference information and leveraging pixel similarity probability distribution as supervisory information. Lastly, we design the Distance Center Alignment (DCA) loss to reduce intra-class variations within and between modalities, enhancing the distinguishability among different identities. Experimental results demonstrate MSALNet’s superior performance over most existing methods on two mainstream VI-ReID datasets and effectively saves computational cost.

With the development of multimedia technology, the secure image retrieval scheme has become a hot research topic. However, how to further improve algorithm performance in the ciphertext needs to be further explored. In this paper, we propose a secure image retrieval scheme based on a deep hash algorithm for index encryption and an improved 4-Dimensional(4-D)hyperchaotic system. The main contributions of this paper are as follows: (1) A novel secure retrieval scheme is proposed to control data transmission. (2) An improved 4-D hyperchaotic system is proposed to preserve privacy. (3) We propose an improved deep pairwise-supervised hashing (DPSH) algorithm and secure kNN to perform index encryption and propose an improved loss function to train the network model. (4) A secure access control scheme is shown, which aims to achieve secure access for users. The experimental results show that the proposed scheme has better retrieval efficiency and better security.

Insulators are widely used in various aspects of the power system and play a crucial role in ensuring the safety and stability of power transmission. Insulator detection is an important measure to guarantee the safety and stability of the transmission system, and accurate localization of insulators is a prerequisite for detection. In this paper, we propose an improved method based on the YOLOv5s model to address the issues of slow localization speed and low accuracy in insulator detection in power systems. In our approach, we first re-cluster the insulator image samples using the k-means algorithm to obtain different sizes of anchor box parameters. Then, we add the non-local attention module (NAM) to the feature extraction module of the YOLOv5s algorithm. The NAM improves the attention mechanism using the weights’ contribution factors and scaling factors. Finally, we recursively replace the ordinary convolution module in the neck network of the YOLOv5 model with the gated normalized convolution (gⁿConv). Through these improvements, the feature extraction capability of the network is enhanced, and the detection performance of YOLOv5s is improved, resulting in increased accuracy and speed in insulator defect localization. In this paper, we conducted training and evaluation on a publicly available dataset of insulator defects. Experimental results show that the proposed improved YOLOv5s model achieves a 1% improvement in localization accuracy compared to YOLOv5. The proposed method balances accuracy and speed, meeting the requirements of online insulator localization in power system inspection.