Baseline Network Research Articles

FA-HRNet: A New Fusion Attention Approach for Vegetation Semantic Segmentation and Analysis

Semantic segmentation of vegetation in aerial remote sensing images is a critical aspect of vegetation mapping. Accurate vegetation segmentation effectively informs real-world production and construction activities. However, the presence of species heterogeneity, seasonal variations, and feature disparities within remote sensing images poses significant challenges for vision tasks. Traditional machine learning-based methods often struggle to capture deep-level features for the segmentation. This work proposes a novel deep learning network named FA-HRNet that leverages the fusion of attention mechanism and a multi-branch network structure for vegetation detection and segmentation. Quantitative analysis from multiple datasets reveals that our method outperforms existing approaches, with improvements in MIoU and PA by 2.17% and 4.85%, respectively, compared with the baseline network. Our approach exhibits significant advantages over the other methods regarding cross-region and cross-scale capabilities, providing a reliable vegetation coverage ratio for ecological analysis.

Early Sweet Potato Plant Detection Method Based on YOLOv8s (ESPPD-YOLO): A Model for Early Sweet Potato Plant Detection in a Complex Field Environment

Traditional methods of pest control for sweet potatoes cause the waste of pesticides and land pollution, but the target detection algorithm based on deep learning can control the precise spraying of pesticides on sweet potato plants and prevent most pesticides from entering the land. Aiming at the problems of low detection accuracy of sweet potato plants and the complex of target detection models in natural environments, an improved algorithm based on YOLOv8s is proposed, which can accurately identify early sweet potato plants. First, this method uses an efficient network model to enhance the information flow in the channel, obtain more effective global features in the high-level semantic structure, and reduce model parameters and computational complexity. Then, cross-scale feature fusion and the general efficient aggregation architecture are used to further enhance the network feature extraction capability. Finally, the loss function is replaced with InnerFocaler-IoU (IFIoU) to improve the convergence speed and robustness of the model. Experimental results showed that the mAP0.5 and model size of the improved network reached 96.3% and 7.6 MB. Compared with the YOLOv8s baseline network, the number of parameters was reduced by 67.8%, the amount of computation was reduced by 53.1%, and the mAP0.5:0.95 increased by 3.5%. The improved algorithm has higher detection accuracy and a lower parameter and calculation amount. This method realizes the accurate detection of sweet potato plants in the natural environment and provides technical support and guidance for reducing pesticide waste and pesticide pollution.

Refined feature enhancement network for object detection

Convolutional neural networks-based object detection techniques have achieved positive performances. However, due to the limitations of local receptive field, some existing object detection methods cannot effectively capture global information in feature extraction phases, and thus lead to unsatisfactory detection performance. Moreover, the feature information extracted by the backbone network may be redundant. To alleviate these problems, in this paper we propose a refined feature enhancement network (RFENet) for object detection. Specifically, we first propose a feature enhancement module (FEM) to capture more global and local information from feature maps with certain long-range dependencies. We further propose a multi-branch dilated attention mechanism (MDAM) to refine the extracted features in a weighted form, which can select more important spatial and channel information and broaden the receptive field of the network. Finally, we validate RFENet on MS-COCO2017, PASCAL VOC2012, and PASCAL VOC07+12 datasets, respectively. Compared to the baseline network, our RFENet improves by 2.4 AP on MS-COCO2017 dataset, 3.4 mAP on PASCAL VOC2012 dataset, and 2.7 mAP on PASCAL VOC07+12 dataset. Extensive experiments show that our RFENet can perform competitively on different datasets. The code is available at https://github.com/object9detection/RFENet.

Hibernation reduces GABA signaling in the brainstem to enhance motor activity of breathing at cool temperatures

BackgroundNeural circuits produce reliable activity patterns despite disturbances in the environment. For this to occur, neurons elicit synaptic plasticity during perturbations. However, recent work suggests that plasticity not only regulates circuit activity during disturbances, but these modifications may also linger to stabilize circuits during future perturbations. The implementation of such a regulation scheme for real-life environmental challenges of animals remains unclear. Amphibians provide insight into this problem in a rather extreme way, as circuits that generate breathing are inactive for several months during underwater hibernation and use compensatory plasticity to promote ventilation upon emergence.ResultsUsing ex vivo brainstem preparations and electrophysiology, we find that hibernation in American bullfrogs reduces GABAA receptor (GABAAR) inhibition in respiratory rhythm generating circuits and motor neurons, consistent with a compensatory response to chronic inactivity. Although GABAARs are normally critical for breathing, baseline network output at warm temperatures was not affected. However, when assessed across a range of temperatures, hibernators with reduced GABAAR signaling had greater activity at cooler temperatures, enhancing respiratory motor output under conditions that otherwise strongly depress breathing.ConclusionsHibernation reduces GABAAR signaling to promote robust respiratory output only at cooler temperatures. Although frogs do not ventilate lungs during underwater hibernation, we suggest this would be beneficial for stabilizing breathing when the animal passes through a large temperature range during emergence in the spring. More broadly, these results demonstrate that compensatory synaptic plasticity can increase the operating range of circuits in harsh environments, thereby promoting adaptive behavior in conditions that suppress activity.

Defect intelligent recognition of membrane product based on deep learning

Defect detection plays a crucial role in the manufacturing industry, ensuring the quality of industrial products. Despite advancements in this field, current defect detection methods face two primary challenges: (1) extracting visually similar features from the background poses difficult and (2) these methods struggle to identify tiny defects in the target objects. We present a feature enhancement module called the SE-CAR, which aims to handle the identified problems effectively. This module is designed to efficiently capture tiny defects in images, prioritize defect information features, and ultimately enhance the model’s predictive performance and accuracy in defect recognition tasks. In addition, Distance-IoU Non-Maximum Suppression is employed as a substitution for the original Non-Maximum Suppression. This enhances the recognition accuracy of bounding boxes, ensuring that the model maintains high detection accuracy even after complex scenarios. Moreover, the proposed methodology exhibits broad applicability across a wide spectrum of prevalent defect detection paradigms. In empirical experiments, we employ the YOLOv7 architecture as the foundation framework, integrating the proposed methodologies for the purpose of detecting defects in the membrane. The empirical evidence demonstrates a notable improvement in the performance of detecting defects in membrane products using the SE-CAR feature enhancement module and Distance-IoU Non-Maximum Suppression algorithm. In comparison to baseline networks, an increase in mAp by 6.29%, precision by 1.63%, and recall by 8.76%.

DeployFusion: A Deployable Monocular 3D Object Detection with Multi-Sensor Information Fusion in BEV for Edge Devices.

To address the challenges of suboptimal remote detection and significant computational burden in existing multi-sensor information fusion 3D object detection methods, a novel approach based on Bird's-Eye View (BEV) is proposed. This method utilizes an enhanced lightweight EdgeNeXt feature extraction network, incorporating residual branches to address network degradation caused by the excessive depth of STDA encoding blocks. Meantime, deformable convolution is used to expand the receptive field and reduce computational complexity. The feature fusion module constructs a two-stage fusion network to optimize the fusion and alignment of multi-sensor features. This network aligns image features to supplement environmental information with point cloud features, thereby obtaining the final BEV features. Additionally, a Transformer decoder that emphasizes global spatial cues is employed to process the BEV feature sequence, enabling precise detection of distant small objects. Experimental results demonstrate that this method surpasses the baseline network, with improvements of 4.5% in the NuScenes detection score and 5.5% in average precision for detection objects. Finally, the model is converted and accelerated using TensorRT tools for deployment on mobile devices, achieving an inference time of 138 ms per frame on the Jetson Orin NX embedded platform, thus enabling real-time 3D object detection.

Exploring the Impact of Architectural Variations in ResNet on CIFAR-100 Performance: An Investigation on Fully Connected Layers, Residual Blocks, and Kernel Size

ResNet is one of the leading neutral networks that has been widely applied in image classification. This study built a simple baseline network based on the concept of ResNet and then examines how variations in ResNet’s architecture affect its model performance to provide insights for optimizing network design. Firstly, this study investigates the number of fully connected layers, the results show that by reducing the number of fully connected layers significantly decreases the total number of trainable parameters, which in turn reduces the training time. However, this reduction does not lead to a noticeable improvement in the accuracy after convergence. In addition, increasing the number of fully connected layers not only greatly increases the training time but also leads to overfitting on the CIFAR-100 dataset, slightly reducing the training performance. Secondly, this study also analyzes the influence of reducing number of residual basic block. Analysis suggests that reducing the use of Residual Blocks has significantly negatively impacted both accuracy and training time. This may be because the use of Residual Blocks positively affects the network’s ability to learn features from the CIFAR-100 dataset. Finally, this study explores the effect of bigger kernel size of convolution layer in Residual Basic Block. The outcome demonstrates increasing the kernel size in the Residual Blocks significantly improves both training time and accuracy. Additionally, it was observed that in this variant experiment, a definitive convergence has not yet been clearly established, leaving the possibility that accuracy might continue to improve with more training epochs.

Vehicular Mini-LED backlight display inspection based on residual global context mechanism

Mini-LED backlight has emerged as a promising technology for high performance LCDs, yet the massive detection of dead pixels and precise LEDs placement are constrained by the miniature scale of the Mini-LEDs. The high-resolution network (Hrnet) with mixed dilated convolution and dense upsampling convolution (MDC-DUC) module and a residual global context attention (RGCA) module has been proposed to detect the quality of vehicular Mini-LED backlights. The proposed model outperforms the baseline networks of Unet, Pspnet, Deeplabv3+, and Hrnet, with a mean intersection over union (Miou) of 86.91%. Furthermore, compared to the four baseline detection networks, our proposed model has a lower root-mean-square error (RMSE) when analyzing the position and defective count of Mini-LEDs in the prediction map by canny algorithm. This work incorporates deep learning to support production lines improve quality of Mini-LED backlights.Graphical abstract

Aero-engine defect detection by integrating attention and multi-scale features

The structural integrity of aircraft engines is related to flight safety. At present, aircraft engine defect detection based on borescope technology is mainly manual operation. In order to improve the detection accuracy and efficiency, an intelligent aircraft engine defect detection algorithm that integrates attention and multi-scale features is proposed to assist borescope work. First, to address the class imbalance problem of defect samples in the original borescope image, a multi- sample fusion data enhancement method based on geometric transformation and Poisson image editing is used to enrich small sample images and construct a defect dataset. Then, the coordinated attention module (CA) is integrated into the baseline network YOLOv5 to emphasize the extraction of defect features and enhance the network's distinction between defect targets and complex backgrounds. A weighted bidirectional feature pyramid structure (BiFPN) is constructed in the neck network to complete higher-level feature fusion and improve the expression ability of multi-scale targets. Finally, the bounding box regression loss function is defined as the EIOU loss to achieve fast and accurate positioning and identification of defect targets. Experimental results show that the average accuracy of defect detection of the proposed algorithm reaches 89.7%, which is improved compared with the baseline network 6.3%, and the size of the trained model is only 14.0 M. Therefore, the proposed method can effectively detect the main defects of aircraft engines.

Image segmentation of tunnel water leakage defects in complex environments using an improved Unet model

Computer vision technology provides an intelligent means for detecting tunnel water leakage areas. However, the accuracy of defect feature extraction and segmentation is limited by factors such as insufficient lighting and environmental interference inside tunnels. To address the problem, this paper proposes a tunnel water leakage area segmentation network model called Customized Side Guided-Unet (CSG-Unet), using Unet as the baseline model. The main contributions are: (1) To improve the accuracy of water leakage area extraction, a customized side guided term is introduced to direct the net’s attention to the changes in light and shade within the image. A parallel attention network module is designed to extract internal information from the guided term. Subsequently, a strengthened channel attention module aggregates the guided term and the original information to achieve accurate segmentation of water leakage areas; (2) To address the scarcity of tunnel water leakage area datasets, a basic dataset is constructed by collecting data from open-source datasets and manually gathered data in tunnels. On this basis, perspective transformation is used to change the camera viewpoint, gaussian noise is randomly added to the images in the dataset to simulate images taken in dimly lit scenes, thereby expanding the dataset and enhancing the network’s generalization. The CSG-Unet network was trained using the constructed training set, achieving a mean Intersection over Union (mi IoU) of 85.54%, a mean Dice coefficient (mi Dice) of 85.26%, and a mean Pixel Accuracy (mi PA) of 90.85%. Compared to its baseline network, U-Net (tiny), these metrics show an improvement of over 3.2% in each indicator. Finally, a visual comparison between the improved network and the baseline network further confirms that the proposed model can effectively adapt to the segmentation of water leakage areas in complex environments.

An efficient multiscale enhancement network with attention mechanism for aluminium defect detection

ABSTRACT Real-time defect detection is required to efficiently control the quality of aluminium. However, aluminium defects have the characteristics of small-size, low contrast, and multiscale variations, which pose great challenges to defect detection. This article aims to improve the defect detection accuracy and propose an effective multiscale enhancement network with attention mechanism for aluminium defect detection (AMMENet). First, to capture key features and mitigate interference from the background, a pluggable parallel residual attention module (PRAM) is proposed for the feature extraction network. To compensate for the loss of deep features, a multilevel semantic enhancement module (C2f-MFF) is proposed to fuse multiscale feature maps. Finally, the model was applied to the Tianchi Aluminium Surface Defect Dataset (TC-ASDD) for ablation experiments and comparisons. The experimental results show that the mean average precision (mAP@0.5) of the proposed AMMENet is 73.6% with a real-time detection speed of 66.2 frames per second (FPS). Compared with YOLOv8 baseline network, AMMENet improves mAP@0.5 by 2.8% with only a slight loss in speed. Moreover, AMMENet is superior to the state-of-the-art detection methods in terms of detection accuracy.

Hibernation reduces GABA signaling in the brainstem to enhance motor activity of breathing at cool temperatures.

Neural circuits produce reliable activity patterns despite disturbances in the environment. For this to occur, neurons elicit synaptic plasticity during perturbations. However, recent work suggests that plasticity not only regulates circuit activity during disturbances, but these modifications may also linger to stabilize circuits during future perturbations. The implementation of such a regulation scheme for real-life environmental challenges of animals remains unclear. Amphibians provide insight into this problem in a rather extreme way, as circuits that generate breathing are inactive for several months during underwater hibernation and use compensatory plasticity to promote ventilation upon emergence. Using ex vivo brainstem preparations and electrophysiology, we find that hibernation in American bullfrogs reduces GABA A receptor (GABA A R) inhibition in respiratory rhythm generating circuits and motor neurons, consistent with a compensatory response to chronic inactivity. Although GABA A Rs are normally critical for breathing, baseline network output at warm temperatures was not affected. However, when assessed across a range of temperatures, hibernators with reduced GABA A R signaling had greater activity at cooler temperatures, enhancing respiratory motor output under conditions that otherwise strongly depress breathing. Hibernation reduces GABA A R signaling to promote robust respiratory output only at cooler temperatures. Although animals do not ventilate lungs during hibernation, we suggest this would be beneficial for stabilizing breathing when the animal passes through a large temperature range during emergence in the spring. More broadly, these results demonstrate that compensatory synaptic plasticity can increase the operating range of circuits in harsh environments, thereby promoting adaptive behavior in conditions that suppress activity.

DLCH-YOLO: An Object Detection Algorithm for Monitoring the Operation Status of Circuit Breakers in Power Scenarios

In the scenario of power system monitoring, detecting the operating status of circuit breakers is often inaccurate due to variable object scales and background interference. This paper introduces DLCH-YOLO, an object detection algorithm aimed at identifying the operating status of circuit breakers. Firstly, we propose a novel C2f_DLKA module based on Deformable Large Kernel Attention. This module adapts to objects of varying scales within a large receptive field, thereby more effectively extracting multi-scale features. Secondly, we propose a Semantic Screening Feature Pyramid Network designed to fuse multi-scale features. By filtering low-level semantic information, it effectively suppresses background interference to enhance localization accuracy. Finally, the feature extraction network incorporates Generalized-Sparse Convolution, which combines depth-wise separable convolution and channel mixing operations, reducing computational load. The DLCH-YOLO algorithm achieved a 91.8% mAP on our self-built power equipment dataset, representing a 4.7% improvement over the baseline network Yolov8. With its superior detection accuracy and real-time performance, DLCH-YOLO outperforms mainstream detection algorithms. This algorithm provides an efficient and viable solution for circuit breaker status detection.

A Systematic Survey on the Application of Artificial Intelligence (ai) Baseline Networks on Grid Computing Techniques - Challenges, Novelty and Prospects

A smart grid is a contemporary electrical system that supports two-way communication and utilizes the concept of demand response. To increase the smart grid's dependability and enhance the consistency, efficiency, and efficiency of the electrical supply, stability prediction is required. The true test for smart grid system designers and specialists will therefore be the increase of renewable energy. To integrate the electric utility infrastructure into the advanced communication era of today, both in terms of function and architecture, this program has made great strides toward modernizing and expanding it. The study reviews how a smart grid applied different deep learning techniques and how renewable energy can be integrated into a system where grid control is essential for energy management. The article discusses the idea of a smart grid and how reliable it is when renewable energy sources are present. Globally, a change in electric energy is needed to reduce greenhouse gas emissions, prevent global warming, reduce pollution, and boost energy security.

YOLOv5_mamba: unmanned aerial vehicle object detection based on bidirectional dense feedback network and adaptive gate feature fusion

Addressing the problem that the object size in Unmanned Aerial Vehicles (UAVs) aerial images is too small and contains limited feature information, leading to existing detection algorithms having less than ideal performance in small object detection, we propose a UAV aerial object detection system named YOLv5_mamba based on bidirectional dense feedback network and adaptive gate feature fusion. This paper improves the You Only Look Once Version 5 (YOLOv5) algorithm by firstly introducing the Faster Implementation of CSP Bottleneck with 2 convolutions (C2f) module from YOLOv8 into the backbone network to enhance the feature extraction capability of the backbone network. Furthermore, the mamba module and C2f module are introduced to construct a bidirectional dense feedback network to enhance the transfer of contextual information in the neck part. Thirdly, an adaptive gate feature fusion network is proposed to improve the head part of YOLOv5 and enhance its final detection capability. Experimental results on the public UAV aerial dataset VisDrone2019 demonstrate that the proposed algorithm improves the detection accuracy by 9.3% compared to the original YOLOv5 baseline network, showing better detection performance for small objects. For the UCAS_AOD dataset, the proposed algorithm outperforms YOLOv5-s by 9%. In the case of the DIOR dataset, the proposed algorithm exceeds YOLOv5-s by 12%.

Narrow road extraction from high-resolution remote sensing images: SWGE-Net and MSIF-Net

ABSTRACT Accurate and complete road network extraction plays a critical role in urban planning, street navigation, and emergency response. At present, narrow roads are a main feature in most public road datasets. However, the continuity and boundary completeness of the extraction results for these narrow roads are relatively poor, due to their varied shapes, uneven spatial distribution, and the presence of various interfering elements. To address these issues, this study introduces a novel network, the Self-weighted Global Context Road Extraction Network (SWGE-Net), which integrates a dilate block and an improved coordinate attention mechanism to effectively capture the complex details and spatial information of narrow roads. Furthermore, most public road training datasets often lack labels for very narrow roads, this omission leads to poor extraction results for these roads in test datasets. In order to further improve the extraction capability for unlabeled, extremely narrow roads, this study introduces another network called the Multi-scale Information Fusion Road Extraction Network (MSIF-Net), which uses the same encoders as SWGE-Net and has a special module for merging information at different scales. This module, with a dilate block and pyramid pooling-based decoder, makes the network better at recognizing and combining features of different sizes. Experimental results indicate that SWGE-Net outperforms the baseline network with road IoU scores of 71.57% and 60.67% on the DeepGlobe and CHN6-CUG road datasets, respectively an improvement of 18.51% and 5.40%. Meanwhile, MSIF-Net not only exceeds the baseline in road IoU scores for both datasets, but also achieves the best performance in extracting unlabeled, extremely narrow roads in qualitative experiments.

Signature-based portfolio allocation: a network approach

Portfolio allocation represents a significant challenge within financial markets, traditionally relying on correlation or covariance matrices to delineate relationships among stocks. However, these methodologies assume time stationarity and only capture linear relationships among stocks. In this study, we propose to substitute the conventional Pearson’s correlation or covariance matrix in portfolio optimization with a similarity matrix derived from the signature. The signature, a concept from path theory, provides a unique representation of time series data, encoding their geometric patterns and inherent properties. Furthermore, we undertake a comparative analysis of network structures derived from the correlation matrix versus those obtained from the signature-based similarity matrix. Through numerical evaluation on the Standard & Poor’s 500, we assess that portfolio allocation utilizing the signature-based similarity matrix yielded superior results in terms of cumulative log-returns and Sharpe ratio compared to the baseline network approach based on Pearson’s correlation. This assessment was conducted across various portfolio optimization strategies. This research contributes to portfolio allocation and financial network representation by proposing the use of signature-based similarity matrices over traditional correlation or covariance matrices.

Modulated deformable convolution based on graph convolution network for rail surface crack detection

Accurate detection of rail surface cracks is essential but also tricky because of the noise, low contrast, and density inhomogeneity. In this paper, to deal with the complex situations in rail surface crack detection, we propose modulated deformable convolution based on a graph convolution network named MDCGCN. The MDCGCN is a novel convolution that calculates the offsets and modulation scalars of the modulated deformable convolution by conducting the graph convolution network on a feature map. The MDCGCN improves the performance of different networks in rail surface crack detection, harming the inference speed slightly. Finally, we demonstrate our methods’ numerical accuracy, computational efficiency, and effectiveness on the public segmentation dataset RSDD and our self-built detection dataset SEU-RSCD and explore an appropriate network structure in the baseline network UNet with the MDCGCN.

The surface deformation of permafrost and active layer thickness in the upper reaches of the Black River basin, revealed by InSAR observations and independent component analysis

The Heihe River Basin, located in the northeastern part of the Qinghai-Tibetan Plateau, is part of the perennial permafrost belt of the Qilian Mountains. Recent observations indicate ongoing permafrost degradation in this region. This study utilizes data from 255 observations provided by Sentinel-1 satellites, MODIS Land Surface Temperature, SMAP-L4 soil moisture data, GNSS measurements, and in situ measurement. We introduced Variational Bayesian independent Component Analysis (VB-ICA) in multi-temporal Interferometric Synthetic Aperture Radar (MT-InSAR) processing to investigate the spatial-temporal characteristics of surface deformation and permafrost active layer thickness (ALT) variations. The analysis demonstrates strong agreement with borehole data and offers improvements over traditional methodologies. The maximum value of ALT in the basin is found to be 5.7 m. VB-ICA effectively delineates seasonal deformations related to the freeze-thaw cycles, with a peak seasonal deformation amplitude of 60 mm. Moreover, the seasonal permafrost's lower boundary reaches an elevation of 3700 m, revealing that permafrost is experiencing widespread degradation and associated soil erosion in the high elevation region of The Heihe River Basin. The paper also explores the efficacy of reference point selection and baseline network establishment for employing the InSAR method in monitoring freeze-thaw deformations. The study underscores the InSAR method's adaptability and its importance for interpreting permafrost deformation and related parameters.

A multi-level collaborative self-distillation learning for improving adaptive inference efficiency

A multi-exit network is an important technique for achieving adaptive inference by dynamically allocating computational resources based on different input samples. The existing works mainly treat the final classifier as the teacher, enhancing the classification accuracy by transferring knowledge to the intermediate classifiers. However, this traditional self-distillation training strategy only utilizes the knowledge contained in the final classifier, neglecting potentially distinctive knowledge in the other classifiers. To address this limitation, we propose a novel multi-level collaborative self-distillation learning strategy (MLCSD) that extracts knowledge from all the classifiers. MLCSD dynamically determines the weight coefficients for each classifier’s contribution through a learning process, thus constructing more comprehensive and effective teachers tailored to each classifier. These new teachers transfer the knowledge back to each classifier through a distillation technique, thereby further improving the network’s inference efficiency. We conduct experiments on three datasets, CIFAR10, CIFAR100, and Tiny-ImageNet. Compared with the baseline network that employs traditional self-distillation, our MLCSD-Net based on ResNet18 enhances the average classification accuracy by 1.18%. The experimental results demonstrate that MLCSD-Net improves the inference efficiency of adaptive inference applications, such as anytime prediction and budgeted batch classification. Code is available at https://github.com/deepzlk/MLCSD-Net.