检索结果-内蒙古大学图书馆

repCrack: An efficient pavement crack segmentation method based on structural re-parameterization

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 141卷

作者： Ni, Minglun Chen, Lei Shi, Peixin ren, Ruiqi Soochow Univ Sch Rail Transportat Suzhou Jiangsu Peoples R China Intelligent Urban Rail Engn Res Ctr Yangzhou Jiangsu Peoples R China

The detection of pavement cracks is a significant challenge in the field of road maintenance. In response to this challenge, the industry has witnessed a growing trend towards the utilization of deep learning-based methods for crack detection. However, existing approaches utilize complex network structures which, while improving accuracy, compromise detection efficiency and hinder practical application. This paper proposes a novel pixel-level pavement crack segmentation model, repCrack, which addresses the current limitations in accuracy and efficiency in pavement crack detection tasks. The proposed model is based on large kernel convolution and multiscale feature extraction, in order to extract more detailed pavement crack information during the training phase. The model building process incorporates structural re-parameterization techniques, including the conversion of multi-branch structures to single on-path structures and the shortening of long sequence structures, which effectively reduces the complexity of the model. Furthermore, to enhance the model's capacity to extract features, an improved coordinate attention mechanism is incorporated to augment the network's focus on the crack region. To validate the detection effect, publicly available datasets, including the Crack Forest Dataset (CFD), German Asphalt Pavement Distress (GAPs) dataset, and Crack Tree dataset, were employed. The experimental results demonstrate that our proposed method exhibits a notable superiority over existing crack detection techniques. For instance, repCrack, with a parameter count of 5.8 million, attains an Intersection over Union (IoU) of 63.8% on the CFD dataset and attains a state-of-the-art methodology (SOTA) performance, exhibiting a 5% enhancement in accuracy and a 68.7% reduction in inference latency in comparison to SegNext.

关键词： Pavement crack detection Semantic segmentation structural re-parameterization Feature fusion Convolutional neural network Civil infrastructure

来源：评论

学校读者我要写书评

暂无评论

repSNet: A Nucleus Instance Segmentation Model Based on Boundary regression and structural re-parameterization

引用

INTERNATIONAL JOURNAL OF COMPUTER VISION 2025年第6期133卷 3222-3241页

作者： Xiong, Shengchun Li, Xiangru Zhong, Yunpeng Peng, Wanfen South China Normal Univ Sch Comp Sci West Zhongshan Ave Guangzhou 510631 Guangdong Peoples R China Signet Therapeut Dept Pediat 289 Digital Peninsula2 Hongliu RdFubao St Shenzhen 518017 Guangdong Peoples R China

Pathological diagnosis is the gold standard for tumor diagnosis, and nucleus instance segmentation is a key step in digital pathology analysis and pathological diagnosis. However, the computational efficiency of the model and the treatment of overlapping targets are the major challenges in the studies of this problem. To this end, a neural network model repSNet was designed based on a nucleus boundary regression and a structural re-parameterization scheme for segmenting and classifying the nuclei in H&E-stained histopathological images. First, repSNet estimates the boundary position information (BPI) of the parent nucleus for each pixel. The BPI estimation incorporates the local information of the pixel and the contextual information of the parent nucleus. Then, the nucleus boundary is estimated by aggregating the BPIs from a series of pixels using a proposed boundary voting mechanism (BVM), and the instance segmentation results are computed from the estimated nucleus boundary using a connected component analysis procedure. The BVM intrinsically achieves a kind of synergistic belief enhancement among the BPIs from various pixels. Therefore, different from the methods available in literature that obtain nucleus boundaries based on a direct pixel recognition scheme, repSNet computes its boundary decisions based on some guidances from macroscopic information using an integration mechanism. In addition, repSNet employs a re-parametrizable encoder-decoder structure. This model can not only aggregate features from some receptive fields with various scales which helps segmentation accuracy improvement, but also reduce the parameter amount and computational burdens in the model inference phase through the structural re-parameterization technique. In the experimental comparisons and evaluations on the Lizard dataset, repSNet demonstrated superior segmentation accuracy and inference speed compared to several typical benchmark models. The experimental code, dataset splitting c

关键词： Neural networks Instance segmentation Pathological images structural re-parameterization

来源：评论

学校读者我要写书评

暂无评论

PUA-Net: end-to-end information hiding network based on structural re-parameterization

引用

APPLIED INTELLIGENCE 2025年第2期55卷 1-15页

作者： Lin, Feng Xue, Ru Dong, Shi Ding, Fuhao Han, Yixin Xizang Minzu Univ Coll Informat Engn Xianyang Peoples R China

Image hiding aims to secretly embed secret information into a cover image and then recover the hidden data with minimal or no loss at the receiving end. Many works on steganography and deep learning have proved the huge prospects of deep learning in the field of image information hiding. However, current deep learning-based steganography research exposes significant limits, among which key issues such as how to improve embedding capacity, imperceptibility, and robustness remain crucial for image-hiding tasks. This article introduces PUA-Net, a new end-to-end neural network model for image steganography. PUA-Net consists of three main components: 1) the CbDw attention module, 2) the attention gate module, and 3) the partial combination convolution module. Each of these components utilizes structural reparameterization operations. In addition, we propose a residual image minimization loss function and use a combination of loss functions based on this loss function. This model can seamlessly embed bit stream information of different capacities into images to generate stego images that are imperceptible to the human eye. Experimental results confirm the effectiveness of our model, achieving an RS-BPP of 5.98 when decoding the extracted secret information and recovering the cover image. When only the extracted secret information is output, the model achieves a maximum RS-BPP of 6.94. Finally, experimental results show that our PUA-Net model outperforms deep learning-based steganography approaches on COCO, ImageNet, and BOSSbase datasets, including GAN-based methods such as Stegastamp and SteganoGAN.

关键词： Image steganography U-net structural re-parameterization

来源：评论

学校读者我要写书评

暂无评论

revisiting Large-Kernel CNN Design via structural re-parameterization for Sensor-Based Human Activity recognition

引用

IEEE SENSORS JOURNAL 2024年第8期24卷 12863-12876页

作者： Yao, Minghui Zhang, Lei Cheng, Dongzhou Qin, Lutong Liu, Xin Fu, Zenan Wu, Hao Song, Aiguo Nanjing Normal Univ Sch Elect & Automat Engn Nanjing 210023 Peoples R China Yunnan Univ Sch Informat Sci & Engn Kunming 650500 Peoples R China

During recent years, human activity recognition (HAR) using smart wearable sensors has become a main research focus in ubiquitous computing scenario. Deep convolutional neural networks (CNNs) have achieved significant success in HAR due to their automatic feature extracting ability in capturing local activity details. Due to superior performance, previous most works always prefer to apply small kernels instead of large kernels to handle time series sensor data for activity recognition. However, they do not intend to answer the key questions: why do large kernels underperform small kernels? How to close the performance gap? Intuitively, benefiting from larger receptive field (RF), larger kernels should have a great potential to model long-range dependencies in time series sensor data. So far, there has been little effort devoted to the larger-kernel design. In this article, we revisit the design of larger-kernel convolutions, which long have been neglected in the context of HAR. We find that both identity shortcut and structural re-parameterization can fully unleash the potential of larger-kernel convolutions. Extensive experiments and ablation studies on four mainstream benchmark datasets including PAMAP2, USC-HAD, UniMiB-SHAR, and OPPORTUNITY, show that our larger-kernel convolutions can further push the limit of small-kernel CNN performances under similar inference time, which can be used a drop-in replacement for small-kernel conv layers. For example, compared to the small-kernel baselines, our proposed approach can consistently boost recognition accuracy by 0.55%, 1.00%, 3.94%, and 1.64% on PAMAP2, USC-HAD, UniMiB-SHAR, and OPPORTUNITY, respectively, which is very competitive among the state-of-the-arts (SOTA). We believe that the incurred high performance is mainly due to larger effective RFs built via large kernels. The practical inference time is evaluated on a real hardware device. Our code can be available at: https://***/MinghuiYao/ELK-HAR/.

关键词： Convolutional neural networks Guidelines Intelligent sensors Convolution human activity recognition (HAR) large kernel sensor structural re-parameterization

来源：评论

学校读者我要写书评

暂无评论

Easy Pruning via Coresets and structural re-parameterization

引用

IEEE SIGNAL PROCESSING LETTERS 2024年 31卷 1725-1729页

作者： Yin, Wenfeng Dong, Gang An, Dianzheng Zhao, Yaqian Wang, Binqiang IEIT Syst Co Ltd Jinan 250101 Peoples R China Shandong First Med Univ Affiliated Hosp 1 Dept Oncol Jinan 250013 Peoples R China

Inference time pruning is characteristic in high construction efficiency, since it dramatically reduces the dependency on finetuning to recover precision. It is adequate to reconstruct compressed convolution kernels by optimizing the loss of feature map reconstruction. However, the accuracy decline of compressed network increases as the loss of feature map reconstruction accumulates layer by layer. To enhance layerwise convolution kernel reconstruction, this paper proposes a hybrid method via combining coresets theory and structural re-parameterization, enabling shallow transfer learning (STL) during inference time pruning. Firstly, our method achieves STL by implementing structural re-parameterization in the process of convolution kernel reconstruction, to adapt to effects of one layer's reconstruction loss on the next layers' inputs. Secondly, a channel-wise scaling process is designed on the basis of coresets theory, to enhance approximation in the mapping from drifted inputs to original feature maps. Selectively, a maximum mean discrepancy based decision-making process is built for switching in two patterns of our method. Tests are executed on image classification and arrhythmia detection. As observed on ImageNet datasets, coresets theory based scaling is more effective at filter level for DenseNet and MobileNet-v2 and resultful at unit kernel level for resNet and SqueezeNet.

关键词： Channel pruning coreset theory structural re-parameterization transfer learning

来源：评论

学校读者我要写书评

暂无评论

A structural re-parameterization NETWORK FOR BEARING FAULT DIAGNOSIS UNDER VARIABLE WORKING CONDITIONS

A STRUCTURAL RE-PARAMETERIZATION NETWORK FOR BEARING FAULT D...

引用

ASME 2024 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC-CIE 2024

作者： Hua, Zehui Dumond, Patrick Department of Mechanical Engineering University of Ottawa Ottawa Canada

ISBN: (纸本)9780791888353

Deep convolutional networks are well known for their strong performance in feature characterization of massive data. Performing intelligent fault diagnosis (IFD) by training an end-to-end model could facilitate the acquisition of health state information of key machinery components while avoiding the need for human intervention and expert knowledge. However, for traditional machine learning, most methods are proposed and implemented based on the assumption that known data collected from the source domain and unknown data collected from the target domain share the same feature distribution, which can hardly be satisfied due to limitations in real industrial applications, as well as variable working conditions. To address this problem, a structural re-parameterization network is proposed, which is used to automatically extract deeper features and minimize the domain discrepancy between the source and target domain by using both metric learning and adversarial learning strategies. To be specific, an initial multi-branched network including shortcut structure is first established. This network enhances feature extraction by fusing features from multiple branches and aligning data when performing IFD under variable working conditions. After completing the training phase, the network can be reparameterized during the inference stage, transitioning into a single-branched network while maintaining identical results, which is much more computationally efficient. Experiments have shown the effectiveness of the proposed method. Copyright © 2024 by ASME.

关键词： intelligent fault diagnosis Bearings deep transfer learning structural re-parameterization Fault diagnosis Parametrization

来源：评论

学校读者我要写书评

暂无评论

SRP&PASMLP-Net: Lightweight skin lesion segmentation network based on structural re-parameterization and parallel axial shift multilayer perceptron

引用

INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY 2024年第2期34卷 e22985-e22985页

作者： Wei, Shuning Chen, Haijun Zhao, Junqi Zhou, Ying Yang, Yimei Hunan Normal Univ Coll Informat Sci & Engn Changsha Peoples R China Hunan Childrens Hosp Data Informat Management Ctr Changsha Peoples R China Hunan Normal Univ Sch Math & Stat Changsha Peoples R China Huaihua Univ Coll Comp & Artificial Intelligence Software Coll Huaihua Hunan Peoples R China Hunan Childrens Hosp Data Informat Management Ctr Changsha 410007 Peoples R China

Accurate skin lesion segmentation (SLS) plays an essential role in the computer-aided diagnosis of skin diseases, for example, melanomas. However, the automated SLS is challenging due to variations in the nature of skin diseases, particularly the ambiguities of boundaries of skin lesion areas (SLAs) and occlusions by hairs. Though many deep learning models, represented by UNet, have been successfully applied to the SLS over the past years, most suffer from inaccurate SLA segmentation with heavy model parameters and slow inferencing speed, hindering their practical applications. To address these challenges, a lightweight SLS network based on structural re-parameterization and parallel axial shift multilayer perceptron (MLP), called SRP&PASMLP-Net, is proposed to achieve powerful segmentation performance with fast inference ability. Specifically, a kind of diverse convolution module, the re-parameterization Diversity Convolution (RDC) block, is proposed in the shallow stage of the segmentation network to enrich the feature space. The inference is performed by structural re-parameterization techniques to decouple the structure at the training and inference stages, thus improving the performance of the model without any inference time cost. In addition, a parallel axial shift MLP (PASMLP) module is proposed, which captures local dependencies by axially shifting the channels of the feature map to capture the information flow from different axes and reduce the network parameters and computational complexity effectively. Extensive experimental results show that the proposed SRP&PASMLP-Net can provide a 4-fold improvement in the inference speed and a 17-fold reduction in model parameters compared with the benchmark network, UNet. It outperforms the state-of-the-art methods on two public datasets, that is, ISIC2018 and PH2, for the SLS.

关键词： lightweight network parallel axial shift MLP skin lesion segmentation structural re-parameterization

来源：评论

学校读者我要写书评

暂无评论

CMB: A Novel structural re-parameterization Block without Extra Training Parameters

CMB: A Novel Structural Re-parameterization Block without Ex...

引用

IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) / IEEE World Congress on Computational Intelligence (IEEE WCCI) / International Joint Conference on Neural Networks (IJCNN) / IEEE Congress on Evolutionary Computation (IEEE CEC)

作者： Zhou, Hengyi Liu, Longjun Zhang, Haonan He, Hongyi Zheng, Nanning Xi An Jiao Tong Univ Inst Artificial Intelligence & Robot Xian Peoples R China

ISBN: (数字)9781728186719

ISBN: (纸本)9781728186719

structural re-parameterization is a raising field, which aims at improving the performance of convolutional neural networks (CNNs) through training an over-parameterization model and transferring it into a compact inference model. However, the performance improvements of prior structural re-parameterization works often come at the cost of heavy extra training resources, which increases carbon emissions and limits the potential applications on large-scale industrial tasks. To this end, first, we conduct experiments with a series of blocks composed of multiple identical branches to investigate the mechanism behind the structural re-parameterization, and then provide an interpretation. Moreover, motivated by the studies of effective receptive fields in the biological visual systems and neural networks, we propose a novel compact block named circular mask block (CMB). Given a neural network, we replace the regular convolutional layer with CMB to construct a training architecture, which can be trained to gain an accuracy boost with No extra training parameters and limited extra training FLOPs. After training, the training architecture can be transformed into the original architecture for inference. Extensive experiments are performed on CIFAR-10 and ImageNet to evaluate the effectiveness of our method. For example, we improve 0.85% top-1 accuracy of resNet-50 on ImageNet without extra training parameters and only 11.32M extra training FLOPs, which saves 434x training FLOPs compared with prior works.

关键词： neural networks convolutional layer structural re-parameterization training parameters

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Image Classification Promotion Using Dynamic Convolution Based on structural re-parameterization

引用

reMOTE SENSING 2023年第23期15卷 5561-5561页

作者： Ding, Chen Li, Xu Chen, Jingyi Xu, Yaoyang Zheng, Mengmeng Zhang, Lei Xian Univ Posts & Telecommun Sch Comp Sci & Technol Xian 710129 Peoples R China Shaanxi Key Lab Network Data Anal & Intelligent Pr Xian 710121 Peoples R China Xian Key Lab Big Data & Intelligent Comp Xian 710121 Peoples R China Northwestern Polytech Univ Sch Comp Sci & Engn Shaanxi Key Lab Speech Image Informat Proc SAIIP Xian 710129 Peoples R China Natl Engn Lab Integrated Aerosp Ground Ocean Big D Xian 710129 Peoples R China

In a hyperspectral image classification (HSIC) task, manually labeling samples requires a lot of manpower and material resources. Therefore, it is of great significance to use small samples to achieve the HSIC task. recently, convolutional neural networks (CNNs) have shown remarkable performance in HSIC, but they still have some areas for improvement. (1) Convolutional kernel weights are determined through initialization and cannot be adaptively adjusted based on the input data. Therefore, it is difficult to adaptively learn the structural features of the input data. (2) The convolutional kernel size is single per layer, which leads to the loss of local information for a large convolutional kernel or global information for a small convolutional kernel. In order to solve the above problems, we propose a plug-and-play method called dynamic convolution based on structural re-parameterization (DCSRP). The contributions of this method are as follows. Firstly, compared with traditional convolution, dynamic convolution is a non-linear function, so it has more representation power. In addition, it can adaptively capture the contextual information of input data. Secondly, the large convolutional kernel and the small convolutional kernel are integrated into a new large convolutional kernel. The large convolutional kernel shares the advantages of the two convolution kernels, which can capture global information and local information at the same time. The results in three publicly available HSIC datasets show the effectiveness of the DCSRP.

关键词： hyperspectral image classification convolutional neural network (CNN) dynamic convolution large kernel structural re-parameterization

来源：评论

学校读者我要写书评

暂无评论

repISD-Net: Learning Efficient Infrared Small-Target Detection Network via structural re-parameterization

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND reMOTE SENSING 2023年 61卷 1页

作者： Wu, Shuanglin Xiao, Chao Wang, Longguang Wang, Yingqian Yang, Jungang An, Wei Natl Univ Def Technol Coll Elect Sci & Technol Changsha 410073 Peoples R China Aviat Univ Air Force Coll Elect Sci & Technol Changchun 130022 Peoples R China

Infrared small-target detection is a challenging task for deep learning-based methods, because targets tend to disappear in the deep layers. To handle this problem, the existing deep neural networks usually apply various dense and skip connections for feature maintenance. Although these well-designed networks have achieved good detection performance, the complex network structures reduce their efficiency. In this article, we propose a simple yet efficient network (repISD-Net) for infrared small-target detection. The core of our repISD-Net is to use different network architectures but equivalent model parameters for training and inference, respectively. Specifically, in the training phase, we design a parallel multibranch edge compensation block (ECB) to enhance the local salient features and capture finer contour characteristic of infrared small targets. In the inference phase, the multibranch topology structures are merged into a single branch with only cascaded 3 x 3 convolutions for fast inference. We conduct extensive experiments on several public datasets to validate the effectiveness of our method. Experimental results demonstrate that our repISD-Net can achieve comparable or even better detection performance with significant acceleration in inference speed as compared with state-of-the-art infrared small-target detection methods. Our code is available at https://***/dalinlin-Wu/repISD-Net.

关键词： Edge extraction efficient inference infrared small-target detection structural re-parameterization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：