Multiscale Interaction Purification-Based Global Context Network for Industrial Process Fault Diagnosis by Yukun Huang, Jianchang Liu, Peng Xu, Lin Jiang, Xiaoyu Sun, Haotian Tang

“…First, we propose a multiscale feature interaction refinement (MFIR) module. The module aims to extract multiscale features enriched with combined information through feature interaction while refining feature representations by employing the efficient channel attention mechanism. …”
Get full text

A Dehazing Method for UAV Remote Sensing Based on Global and Local Feature Collaboration by Chenyang Li, Suiping Zhou, Ting Wu, Jiaqi Shi, Feng Guo

“…In parallel, a local information extraction sub-network equipped with an Adaptive Local Information Enhancement (ALIE) module is used to refine texture and edge details. …”
Get full text

PR-CLIP: Cross-Modal Positional Reconstruction for Remote Sensing Image–Text Retrieval by Jihong Guan, Yulou Shu, Wengen Li, Zihan Song, Yichao Zhang

“…Specifically, PR-CLIP first uses a cross-modal positional information extraction module to extract the complementary features between images and texts. …”
Get full text

Learning From Natural Images in Few-Shot SAR Target Classification by Songhao Shi, Xiaodan Wang, Yafei Song

“…To further address the challenge of category confusion in SAR images, we introduce an embedding space reconstruction module. This module utilizes supervised contrastive learning to enhance intraclass compactness and interclass divergence of features. …”
Get full text

Error Mitigation Teacher for Semi-Supervised Remote Sensing Object Detection by Junhong Lu, Hao Chen, Pengfei Gao, Yu Wang

“…EMT consists of three lightweight modules. First, the Adaptive Pseudo-Label Filtering (APLF) module removes noisy pseudo boxes via a second-stage RCNN and adjusts class-specific thresholds through dynamic confidence filtering. …”
Get full text

SERNet: Spatially Enhanced Recalibration Network for Building Extraction in Dense Remote Sensing Scenes by Kuikui Han, Yuanwei Yang, Xianjun Gao, Dongjie Yang, Lei Xu

“…The rapid development of urban and rural construction has accelerated the demand for segmentation in dense building scenes. However, the issue of inaccurate building localization in such scenes still lacks effective solutions. …”
Get full text

DADNet: text detection of arbitrary shapes from drone perspective based on boundary adaptation by Jun Liu, Jianxun Zhang, Ting Tang, Shengyuan Wu

“…Using ResNet50 as the backbone network, we introduce the proposed Hybrid Text Attention Mechanism into the backbone network to enhance the perception of text regions in the feature extraction module. Additionally, we propose a Spatial Feature Fusion Module to adaptively fuse text features of different scales, thereby enhancing the model’s adaptability. …”
Get full text

A Lightweight Pavement Defect Detection Algorithm Integrating Perception Enhancement and Feature Optimization by Xiang Zhang, Xiaopeng Wang, Zhuorang Yang

“…The algorithm first designs the Receptive-Field Convolutional Block Attention Module Convolution (RFCBAMConv) and the Receptive-Field Convolutional Block Attention Module C2f-RFCBAM, based on which we construct an efficient Perception Enhanced Feature Extraction Network (PEFNet) that enhances multi-scale feature extraction capability by dynamically adjusting the receptive field. …”
Get full text

GDSN-CD: Graph-Guided Diffusion Synergistic Network for Remote Sensing Change Detection by Yunfei Zhu, Jintao Song, Jinjiang Li

“…Furthermore, we propose a hierarchical dynamic fusion module that adaptively fuses multilevel features to coordinate the complementary relationship between texture and semantics; and design a dual-feature dynamic selection module that optimizes the fusion of differential and additive features through adaptive weighting, accurately enhancing change signals while suppressing background interference. …”
Get full text

Application of CycleGAN-based low-light image enhancement algorithm in foreign object detection on belt conveyors in underground mines by Anxin Zhao, Qiuhong Zheng, Liang Li

“…Finally, a dynamic effective self-attention aggregation module is designed to suppress the generation of noise and artifacts. …”
Get full text

BiEHFFNet: A Water Body Detection Network for SAR Images Based on Bi-Encoder and Hybrid Feature Fusion by Bin Han, Xin Huang, Feng Xue

“…Additionally, the convolutional block attention module (CBAM) is employed to suppress irrelevant information of the output features of each ResNet stage. …”
Get full text

Influence of Climatic Parameters on the Photovoltaic Conversion Efficiency of a Polycrystalline Solar Panel by N.K. Tanasheva, A.A. Potapova, L.L. Minkov, A.S. Tussypbayeva, A.N. Dyusembaeva, E.K. Mussenova, B.B. Kutum, A.Z. Tleubergenova

“…Therefore, depending on the region and time of year, the same solar module will have different performance. Based on this, an urgent issue when planning the use of solar panels is the possibility of determining how much the efficiency of photovoltaic conversion in a particular area will decrease. …”
Get full text

Adversarial patch defense algorithm based on PatchTracker by Zhenjie XIAO, Shiyu HUANG, Feng YE, Liqing HUANG, Tianqiang HUANG

“…The application of deep neural networks in target detection has been widely adopted in various fields.However, the introduction of adversarial patch attacks, which add local perturbations to images to mislead deep neural networks, poses a significant threat to target detection systems based on vision techniques.To tackle this issue, an adversarial patch defense algorithm based on PatchTracker was proposed, leveraging the semantic differences between adversarial patches and image backgrounds.This algorithm comprised an upstream patch detector and a downstream data enhancement module.The upstream patch detector employed a YOLOV5 (you only look once-v5) model with attention mechanism to determine the locations of adversarial patches, thereby improving the detection accuracy of small-scale adversarial patches.Subsequently, the detected regions were covered with appropriate pixel values to remove the adversarial patches.This module effectively reduced the impact of adversarial examples without relying on extensive training data.The downstream data enhancement module enhanced the robustness of the target detector by modifying the model training paradigm.Finally, the image with removed patches was input into the downstream YOLOV5 target detection model, which had been enhanced through data augmentation.Cross-validation was performed on the public TT100K traffic sign dataset.Experimental results demonstrated that the proposed algorithm effectively defended against various types of generic adversarial patch attacks when compared to situations without defense measures.The algorithm improves the mean average precision (mAP) by approximately 65% when detecting adversarial patch images, effectively reducing the false negative rate of small-scale adversarial patches.Moreover, compared to existing algorithms, this approach significantly enhances the accuracy of neural networks in detecting adversarial samples.Additionally, the method exhibited excellent compatibility as it does not require modification of the downstream model structure.…”
Get full text

S²RCFormer: Spatial-Spectral Residual Cross-Attention Transformer for Multimodal Remote Sensing Data Classification by Yifei Xu, Lingming Cao, Jialu Li, Wenlong Li, Yaochen Li, Yingjie Zong, Aichen Wang, Yuan Rao, Shuiguang Deng

“…It mainly consists of a patchwise convolutional module (PTConv), pixelwise convolutional module (PXConv), residual cross-attention tokenization module (RCTM), and transformer feature fusion module (TFFM). …”
Get full text

CNN Based Fault Classification and Predition of 33kw Solar PV System with IoT Based Smart Data Collection Setup by K. Punitha, G. Sivapriya, T. Jayachitra

“…The real-time data from the PV system for five years, covering 23,000 instances of eight types of faults such as Cell Cracks or Hot Spots, Partial Shading, sensor fault, Module failure, Ground Faults, Communication Errors, Environmental Factors, Grid Connectivity Issues are collected. …”
Get full text

Research on the Real-Time Scoring of Chest Ring Target Based on Transfer Learning and Improved Lightweight Neural Network by Minghui Meng, Chuande Zhou

“…To achieve real-time scoring of chest ring targets during outdoor shooting training while addressing the issues of limited memory and low performance in portable devices, this paper proposes a real-time scoring method for chest ring targets based on an improved lightweight neural network architecture. …”
Get full text

LG-YOLOv8: A Lightweight Safety Helmet Detection Algorithm Combined with Feature Enhancement by Zhipeng Fan, Yayun Wu, Wei Liu, Ming Chen, Zeguo Qiu

“…In the realm of construction site monitoring, ensuring the proper use of safety helmets is crucial. Addressing the issues of high parameter values and sluggish detection speed in current safety helmet detection algorithms, a feature-enhanced lightweight algorithm, LG-YOLOv8, was introduced. …”
Get full text

A Hybrid Framework for Referring Image Segmentation: Dual-Decoder Model with SAM Complementation by Haoyuan Chen, Sihang Zhou, Kuan Li, Jianping Yin, Jian Huang

“…This framework incorporates an MLP decoder and a KAN decoder with a multi-scale feature fusion module, enhancing the model’s capacity to discern fine details within images. …”
Get full text

An Efficient Bidirectional Android Translation Prototype for Yemeni Sign Language Using Fuzzy Logic and CNN Transfer Learning Models by Mogeeb A. A. Mosleh, Abdu H. Gumaei

“…The prototype consists of two primary modules for translating text to sign language and vice versa in both directions. …”
Get full text

YOLOv9-GSSA model for efficient soybean seedlings and weeds detection by Baihe Liang, Liangchen Hu, Guangxing Liu, Peng Hu, Shaosheng Xu, Biao Jie

“…Additionally, the GSSA neck optimization module, combining GSConv and Gated Self-Attention, supports key information extraction and multi-scale feature interaction. …”
Get full text