期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到33篇文章
< 1 2 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
An Adaptive Multi-Scale Dilated Convolution Network for Real-Time Road Black Ice Detection 认领 引用
1
作者 Sun-Kyoung Kang Yeonwoo Lee 《Computers, Materials & Continua》 SCIE EI 2026年第8期1742-1768,共27页
Black ice formation on road surfaces presents a serious hazard due to its low visibility and high slipperiness,underscoring the critical need for timely and accurate detection in intelligent transportation systems.In ... Black ice formation on road surfaces presents a serious hazard due to its low visibility and high slipperiness,underscoring the critical need for timely and accurate detection in intelligent transportation systems.In this paper,we propose AdaMsDCNet,an adaptive multi-scale dilated convolution network designed for real-time black-ice semantic segmentation on resource-constrained edge platforms,applying a Convolutional Neural Network(CNN)with an adaptive Multi-Scale Dilated Convolution(MsDC)feature fusion encoder-decoder architecture.The key concept of AdaMsDCNet is to employ an encoder-decoder architecture with parallel multi-scale dilated convolutional paths that adjust dilation rates at different encoder depths using a systematic 4→2→1 progression,optimally capturing a wide range of receptive fields while mitigating checkerboard artifacts.The encoder dynamically fuses features from multiple dilation rates at each stage,enhancing segmentation accuracy.Simultaneously,the decoder uses transposed convolutions and skip connections to preserve fine spatial details.Experimental validation on a proprietary thermal infrared dataset of 1156 annotated images show that AdaMsDCNet_9 achieves 96.47%mIoU,95.48%Black-Ice IoU,97.55%Precision,97.82%Recall,and 97.69%F1-Score,outperforming U-Net(+26.78 pp mIoU,+29.88 pp Recall),DeepLabv3+(+2.82 pp mIoU),and LinkNet(+1.08 pp mIoU)while requiring only 1.86M parameters and maintaining real-time inference speeds of 3.94~5.63 FPS on the NVIDIA Jetson Nano embedded GPU.Ablation studies confirm the benefits of adaptive dilation,parallel feature fusion,and controlled channel growth for the accuracy–efficiency trade-off.Limitations including dataset generalization to uncontrolled outdoor conditions and the evaluation of imbalance-aware loss functions are identified as directions for future work. 展开更多
关键词 CNN multi-scale dilation convolution feature fusion black ice detection
暂未订购 下载PDF
Improved multi-scale feature fusion for infrared small target detection based on YOLOv8 认领 引用
2
作者 DING Shangsi YANG Guiqin GAN Bingkun 《Journal of Measurement Science and Instrumentation》 CAS CSCD 2026年第2期208-218,共11页
Aiming at the problems of low target pixels and intricate background in small target detection in infrared scenes,a target detection model based on multi-scale feature extraction with YOLOv8 was proposed.Firstly,all d... Aiming at the problems of low target pixels and intricate background in small target detection in infrared scenes,a target detection model based on multi-scale feature extraction with YOLOv8 was proposed.Firstly,all downsampling convolutions in the network were replaced with the Haar wavelet downsampling(HWD)module to better preserve fine-grained details in infrared imagery during downsampling.Secondly,the spatial pyramid pooling-fast(SPPF)module was improved by introducing separable convolutions,which expanded the receptive field in both horizontal and vertical directions,enabling more comprehensive spatial information capture.Furthermore,a novel C2f_CDWR module was designed using dilated convolutions with varying dilation rates to achieve adaptive feature extraction across multiple receptive fields,thus enhancing detection performance for objects of different sizes.Finally,to improve localization accuracy,the original CIoU loss in YOLOv8 was replaced with Inner-SIoU,which effectively improved bounding box regression accuracy and significantly boosted the model’s capability in detecting small infrared targets.The experimental evaluation on the HIT-UAV dataset shows that the precision of the enhanced YOLOv8 model is 90.5%,the recall rate is 75.9%,and the mean average precision is 85.7%.In terms of infrared target detection,its performance was significantly better than that of the baseline YOLOv8 model and other benchmark models. 展开更多
关键词 infrared image small object detection multi-scale feature extraction dilation convolution YOLOv8v8
暂未订购 下载PDF
A Lightweight Convolutional Neural Network with Hierarchical Multi-Scale Feature Fusion for Image Classification 认领 引用 被引量：2
3
作者 Adama Dembele Ronald Waweru Mwangi Ananda Omutokoh Kube 《Journal of Computer and Communications》 2024年第2期173-200,共28页
Convolutional neural networks (CNNs) are widely used in image classification tasks, but their increasing model size and computation make them challenging to implement on embedded systems with constrained hardware reso... Convolutional neural networks (CNNs) are widely used in image classification tasks, but their increasing model size and computation make them challenging to implement on embedded systems with constrained hardware resources. To address this issue, the MobileNetV1 network was developed, which employs depthwise convolution to reduce network complexity. MobileNetV1 employs a stride of 2 in several convolutional layers to decrease the spatial resolution of feature maps, thereby lowering computational costs. However, this stride setting can lead to a loss of spatial information, particularly affecting the detection and representation of smaller objects or finer details in images. To maintain the trade-off between complexity and model performance, a lightweight convolutional neural network with hierarchical multi-scale feature fusion based on the MobileNetV1 network is proposed. The network consists of two main subnetworks. The first subnetwork uses a depthwise dilated separable convolution (DDSC) layer to learn imaging features with fewer parameters, which results in a lightweight and computationally inexpensive network. Furthermore, depthwise dilated convolution in DDSC layer effectively expands the field of view of filters, allowing them to incorporate a larger context. The second subnetwork is a hierarchical multi-scale feature fusion (HMFF) module that uses parallel multi-resolution branches architecture to process the input feature map in order to extract the multi-scale feature information of the input image. Experimental results on the CIFAR-10, Malaria, and KvasirV1 datasets demonstrate that the proposed method is efficient, reducing the network parameters and computational cost by 65.02% and 39.78%, respectively, while maintaining the network performance compared to the MobileNetV1 baseline. 展开更多
关键词 MobileNet Image Classification Lightweight Convolutional Neural Network Depthwise Dilated Separable Convolution Hierarchical Multi-Scale Feature Fusion
暂未订购 下载PDF
Chinese named entity recognition with multi-network fusion of multi-scale lexical information 认领 引用 被引量：3
4
作者 Yan Guo Hong-Chen Liu +3 位作者 Fu-Jiang Liu Wei-Hua Lin Quan-Sen Shao Jun-Shun Su 《Journal of Electronic Science and Technology》 EI CAS CSCD 2024年第4期53-80,共28页
Named entity recognition(NER)is an important part in knowledge extraction and one of the main tasks in constructing knowledge graphs.In today’s Chinese named entity recognition(CNER)task,the BERT-BiLSTM-CRF model is ... Named entity recognition(NER)is an important part in knowledge extraction and one of the main tasks in constructing knowledge graphs.In today’s Chinese named entity recognition(CNER)task,the BERT-BiLSTM-CRF model is widely used and often yields notable results.However,recognizing each entity with high accuracy remains challenging.Many entities do not appear as single words but as part of complex phrases,making it difficult to achieve accurate recognition using word embedding information alone because the intricate lexical structure often impacts the performance.To address this issue,we propose an improved Bidirectional Encoder Representations from Transformers(BERT)character word conditional random field(CRF)(BCWC)model.It incorporates a pre-trained word embedding model using the skip-gram with negative sampling(SGNS)method,alongside traditional BERT embeddings.By comparing datasets with different word segmentation tools,we obtain enhanced word embedding features for segmented data.These features are then processed using the multi-scale convolution and iterated dilated convolutional neural networks(IDCNNs)with varying expansion rates to capture features at multiple scales and extract diverse contextual information.Additionally,a multi-attention mechanism is employed to fuse word and character embeddings.Finally,CRFs are applied to learn sequence constraints and optimize entity label annotations.A series of experiments are conducted on three public datasets,demonstrating that the proposed method outperforms the recent advanced baselines.BCWC is capable to address the challenge of recognizing complex entities by combining character-level and word-level embedding information,thereby improving the accuracy of CNER.Such a model is potential to the applications of more precise knowledge extraction such as knowledge graph construction and information retrieval,particularly in domain-specific natural language processing tasks that require high entity recognition precision. 展开更多
关键词 Bi-directional long short-term memory(BiLSTM) Chinese named entity recognition(CNER) Iterated dilated convolutional neural network(IDCNN) Multi-network integration Multi-scale lexical features
暂未订购 下载PDF
Two Stages Segmentation Algorithm of Breast Tumor in DCE-MRI Based on Multi-Scale Feature and Boundary Attention Mechanism 认领 引用
5
作者 Bing Li Liangyu Wang +3 位作者 Xia Liu Hongbin Fan Bo Wang Shoudi Tong 《Computers, Materials & Continua》 SCIE EI 2024年第7期1543-1561,共19页
Nuclearmagnetic resonance imaging of breasts often presents complex backgrounds.Breast tumors exhibit varying sizes,uneven intensity,and indistinct boundaries.These characteristics can lead to challenges such as low a... Nuclearmagnetic resonance imaging of breasts often presents complex backgrounds.Breast tumors exhibit varying sizes,uneven intensity,and indistinct boundaries.These characteristics can lead to challenges such as low accuracy and incorrect segmentation during tumor segmentation.Thus,we propose a two-stage breast tumor segmentation method leveraging multi-scale features and boundary attention mechanisms.Initially,the breast region of interest is extracted to isolate the breast area from surrounding tissues and organs.Subsequently,we devise a fusion network incorporatingmulti-scale features and boundary attentionmechanisms for breast tumor segmentation.We incorporate multi-scale parallel dilated convolution modules into the network,enhancing its capability to segment tumors of various sizes through multi-scale convolution and novel fusion techniques.Additionally,attention and boundary detection modules are included to augment the network’s capacity to locate tumors by capturing nonlocal dependencies in both spatial and channel domains.Furthermore,a hybrid loss function with boundary weight is employed to address sample class imbalance issues and enhance the network’s boundary maintenance capability through additional loss.Themethod was evaluated using breast data from 207 patients at RuijinHospital,resulting in a 6.64%increase in Dice similarity coefficient compared to the benchmarkU-Net.Experimental results demonstrate the superiority of the method over other segmentation techniques,with fewer model parameters. 展开更多
关键词 Dynamic contrast-enhanced magnetic resonance imaging(DCE-MRI) breast tumor segmentation multi-scale dilated convolution boundary attention the hybrid loss function with boundary weight
暂未订购 下载PDF
Attention-enhanced multi-time scale LSTM for soft sensor modeling of corn starch liquefaction 认领 引用
6
作者 Yu Zhuang Zhongyi Zhang +5 位作者 Jin Tao Yi Li Fan Li Yu Wang Lei Zhang Jian Du 《Chinese Journal of Chemical Engineering》 SCIE EI CAS CSCD 2026年第1期132-144,共13页
Data-driven deep learning modeling has been increasingly applied to quality prediction in complex chemical processes.However,the data show complex temporal features due to different residence times and strong coupling... Data-driven deep learning modeling has been increasingly applied to quality prediction in complex chemical processes.However,the data show complex temporal features due to different residence times and strong coupling relationships among chemical entities.This study proposes a multi-scale temporal feature extraction module to extract local dynamic temporal features across different time scales and combines it with long short-term memory(LSTM)networks to capture global temporal patterns,thereby taking full advantage of available data.In addition,variable-wise channel attention is integrated into the model to enhance attention on the essential parts of the feature maps and improve predictive performance.Furthermore,by analyzing the attention weights,the model quickly identifies the key variables that significantly affect the predictions.Finally,the model is applied to a real corn starch liquefaction process and achieves an accurate product quality prediction with an R2 value of 0.9392,which represents a 4%to 9%improvement over traditional models and demonstrates the superiority of the proposed approach. 展开更多
关键词 Multi-scale dilated causal convolution Neural networks Soft sensor Systems engineering attention mechanism Biochemical engineering
暂未订购 下载PDF
基于多尺度特征增强的改进YOLOv11n桑蚕健康状态实时检测研究 认领 引用
7
作者 易云飞 史英杰 +2 位作者 陈旺 施丽媛 史翔宇 《电子技术应用》 2026年第7期142-150,共9页
为解决传统桑蚕养殖中病蚕识别滞后、检测精度不足的问题,提出一种改进YOLOv11n的桑蚕健康状态检测方法(MSDA-YOLO)。该方法的核心创新包括:(1)在主干网络中引入多尺度分组空洞卷积(Multi-scale Grouped Dilated Convolution,MSGDC)与C... 为解决传统桑蚕养殖中病蚕识别滞后、检测精度不足的问题,提出一种改进YOLOv11n的桑蚕健康状态检测方法(MSDA-YOLO)。该方法的核心创新包括:(1)在主干网络中引入多尺度分组空洞卷积(Multi-scale Grouped Dilated Convolution,MSGDC)与C3k2结合设计了C3k2MS模块,以提升对不同尺度特征的提取能力;(2)首次在桑蚕检测研究中引入DySample动态上采样器,提高在密集场景下对蚕体的空间细节感知与几何结构保持能力;(3)使用自适应空间特征融合策略(Adaptively Spatial Feature Fusion,ASFF)改造YOLOv11的检测头,优化多尺度特征融合效能,抑制尺度间特征冲突。实验结果表明,MSDA-YOLO在多项评估指标上均表现出色。具体而言,该方法在精确率上达到87.0%,召回率为77.8%,mAP@0.5为87.3%,mAP@0.5:0.95为52.8%,均领先于基线模型YOLOv11n和目前主流的YOLO系列检测模型,在桑蚕健康检测方面具有明显优势。 展开更多
关键词 YOLOv11n 多尺度分组空洞卷积 DySample 自适应空间特征融合
暂未订购 下载PDF
Hard-rock tunnel lithology identification using multiscale dilated convolutional attention network based on tunnel face images 认领 引用 被引量：5
8
作者 Wenjun ZHANG Wuqi ZHANG +5 位作者 Gaole ZHANG Jun HUANG Minggeng LI Xiaohui WANG Fei YE Xiaoming GUAN 《Frontiers of Structural and Civil Engineering》 SCIE EI CSCD 2023年第12期1796-1812,共17页
For real-time classification of rock-masses in hard-rock tunnels,quick determination of the rock lithology on the tunnel face during construction is essential.Motivated by current breakthroughs in artificial intellige... For real-time classification of rock-masses in hard-rock tunnels,quick determination of the rock lithology on the tunnel face during construction is essential.Motivated by current breakthroughs in artificial intelligence technology in machine vision,a new automatic detection approach for classifying tunnel lithology based on tunnel face images was developed.The method benefits from residual learning for training a deep convolutional neural network(DCNN),and a multi-scale dilated convolutional attention block is proposed.The block with different dilation rates can provide various receptive fields,and thus it can extract multi-scale features.Moreover,the attention mechanism is utilized to select the salient features adaptively and further improve the performance of the model.In this study,an initial image data set made up of photographs of tunnel faces consisting of basalt,granite,siltstone,and tuff was first collected.After classifying and enhancing the training,validation,and testing data sets,a new image data set was generated.A comparison of the experimental findings demonstrated that the suggested approach outperforms previous classifiers in terms of various indicators,including accuracy,precision,recall,F1-score,and computing time.Finally,a visualization analysis was performed to explain the process of the network in the classification of tunnel lithology through feature extraction.Overall,this study demonstrates the potential of using artificial intelligence methods for in situ rock lithology classification utilizing geological images of the tunnel face. 展开更多
关键词 hard-rock tunnel face intelligent lithology identification multi-scale dilated convolutional attention network image classification deep learning
暂未订购 下载PDF
基于DGC-SwinT的轴承故障诊断轻量化方法 认领 引用
9
作者 何良钊 姚娅川 《四川轻化工大学学报（自然科学版）》 CAS 2026年第2期24-34,共11页
针对传统滚动轴承故障诊断方法在强噪声环境下特征提取和泛化能力不足以及模型参数量过大的问题,本文从时频特征增强与深度特征解耦的角度提出一种基于膨胀分组卷积(DGC)和Swin Transformer(SwinT)的轻量化轴承故障诊断方法。首先,针对... 针对传统滚动轴承故障诊断方法在强噪声环境下特征提取和泛化能力不足以及模型参数量过大的问题,本文从时频特征增强与深度特征解耦的角度提出一种基于膨胀分组卷积(DGC)和Swin Transformer(SwinT)的轻量化轴承故障诊断方法。首先,针对故障冲击在时频域的瞬态突变特征,采用同步压缩小波变换构建时频敏感特征空间,这种方法可以有效地突出信号中的关键特征,抑制次要信息和干扰项;其次,设计了多尺度特征融合模块,该模块从时频信号中充分提取低级特征,通过DGC降低模型计算量;然后通过故障调制产生的跨尺度依赖关系构建高阶信息交互块对重要特征进行加权,依托SwinT模型捕获全局依赖关系的优势,深度挖掘长程周期性故障信息;最后,通过CWRU轴承数据集和SEU轴承数据集进行实验。实验结果表明所提方法在存在噪声干扰信号条件下准确率高达99%,具有高度鲁棒性。该方法为旋转机械的在线监测系统提供了新的技术参考,特别适用于风电齿轮箱、高铁牵引电机等复杂工况下的早期故障预警。 展开更多
关键词 滚动轴承 故障诊断 轻量化 膨胀分组卷积 Swin Transformer 多尺度特征融合
暂未订购 下载PDF
基于小波变换与残差分组空洞卷积的多聚焦图像融合方法 认领 引用
10
作者 曹皓阁 吴丽丽 《软件工程》 2026年第8期29-34,39,共6页
多聚焦图像融合任务旨在将同一场景下不同聚焦区域的图像融合成全焦段图像。传统图像融合策略依赖固定小波基或深度学习进行特征提取和融合,灵活性差,难以在复杂应用场景下有良好的融合效果,融合图像物体边缘信息损失或重复叠加,融合后... 多聚焦图像融合任务旨在将同一场景下不同聚焦区域的图像融合成全焦段图像。传统图像融合策略依赖固定小波基或深度学习进行特征提取和融合,灵活性差,难以在复杂应用场景下有良好的融合效果,融合图像物体边缘信息损失或重复叠加,融合后产生残影重影现象。因此提出一种基于小波变换与残差分组空洞卷积的多聚焦图像融合方法,结合可学习平稳小波变换(LSWT)与多子带梯度选择策略,有效提升融合图像的边缘清晰度与细节完整性,通过保留低频结构信息与高频细节,避免传统小波变换对图像进行下采样导致的信息损失,增强特征表达、捕捉多尺度信息,综合提升模型对多聚焦图像特征的提取与融合能力及泛化性。实验结果表明:与传统融合算法相比,本文方法在峰值信噪比(PSNR)方面平均提升约7%~18%,在SSIM方面均值突破0.976,提升约0.5%~9%,在NMI方面提升约1.5%~5%,显著增强了像素级重构、结构信息保留及多源图像信息整合能力,在图像物体边缘处理、细节信息保留方面具有优势,客观评价指标和主观评价与标准图像非常接近。 展开更多
关键词 多聚焦图像融合 可学习平稳小波变换 多子带梯度选择 残差分组空洞卷积块
暂未订购 下载PDF
基于全局双组注意力的红外与可见光图像融合 认领 引用 被引量：2
11
作者 赵阳 杨文贵 高翠云 《液晶与显示》 CAS CSCD 北大核心 2025年第12期1840-1852,共13页
复杂场景下,融合模型常难以充分提取红外图像的全局大尺度结构和可见光图像的局部小尺度细节特征并将其协同融合,导致融合效果不佳。本文提出基于尺度分工的协同融合原则,设计了一种新的基于自编码器结构的融合模型,模型的编码器和解码... 复杂场景下,融合模型常难以充分提取红外图像的全局大尺度结构和可见光图像的局部小尺度细节特征并将其协同融合,导致融合效果不佳。本文提出基于尺度分工的协同融合原则,设计了一种新的基于自编码器结构的融合模型,模型的编码器和解码器采用卷积神经网络(CNN)架构。该模型利用全局双组注意力机制,将特征图在长度和宽度方向上分组提取信息后,通过跨通道双组注意力图对特征图进行加权,生成包含更多全局大尺度结构信息的新特征图,实现多个维度的图像信息提取;利用多尺度空洞池化卷积机制,通过多种尺寸的感受野以及实施全局平均、中值池化操作,实现图像中的局部小尺度特征信息提取;利用解码器整合密集连接层和跳跃连接的大尺度结构和小尺度细节特征,使它们协同融合,重建得到融合图像。实验结果表明,该方法在MSRS和TNO数据集上,与其他方法相比,信息熵、平均梯度、边缘强度分别提升了0.95%、6.28%、6.19%和1.75%、13.51%、11.75%。空间频率在MSRS数据集上提升了4.61%,在TNO数据集上仅次于MDLSR-RFM方法,有效提升了复杂场景下的融合图像质量,同时也具有良好的稳定性和泛化能力。 展开更多
关键词 红外与可见光图像融合 图像增强 全局双组注意力 空洞卷积
暂未订购 下载PDF
Deep Learning-Based Algorithm for Robust Object Detection in Flooded and Rainy Environments 认领 引用
12
作者 Pengfei Wang Jiwu Sun +4 位作者 Lu Lu Hongchen Li Hongzhe Liu Cheng Xu Yongqiang Liu 《Computers, Materials & Continua》 SCIE EI 2025年第8期2883-2903,共21页
Flooding and heavy rainfall under extreme weather conditions pose significant challenges to target detection algorithms.Traditional methods often struggle to address issues such as image blurring,dynamic noise interfe... Flooding and heavy rainfall under extreme weather conditions pose significant challenges to target detection algorithms.Traditional methods often struggle to address issues such as image blurring,dynamic noise interference,and variations in target scale.Conventional neural network(CNN)-based target detection approaches face notable limitations in such adverse weather scenarios,primarily due to the fixed geometric sampling structures that hinder adaptability to complex backgrounds and dynamically changing object appearances.To address these challenges,this paper proposes an optimized YOLOv9 model incorporating an improved deformable convolutional network(DCN)enhanced with a multi-scale dilated attention(MSDA)mechanism.Specifically,the DCN module enhances themodel’s adaptability to target deformation and noise interference by adaptively adjusting the sampling grid positions,while also integrating feature amplitude modulation to further improve robustness.Additionally,theMSDA module is introduced to capture contextual features acrossmultiple scales,effectively addressing issues related to target occlusion and scale variation commonly encountered in flood-affected environments.Experimental evaluations are conducted on the ISE-UFDS and UA-DETRAC datasets.The results demonstrate that the proposedmodel significantly outperforms state-of-the-art methods in key evaluation metrics,including precision,recall,F1-score,and mAP(Mean Average Precision).Notably,the model exhibits superior robustness and generalization performance under simulated severe weather conditions,offering reliable technical support for disaster emergency response systems.This study contributes to enhancing the accuracy and real-time capabilities of flood early warning systems,thereby supporting more effective disaster mitigation strategies. 展开更多
关键词 YOLO vehicle detection flood deformable convolutional networks multi-scale dilated attention
暂未订购 下载PDF
基于Swin Transformer的输电通道外破目标快速识别方法 认领 引用
13
作者 郑城市 李健 +3 位作者 张本 黄永 张颜 郭宁 《湖北电力》 2025年第4期111-119,共9页
针对输电通道外力破坏目标识别中低对比度特征提取困难、导线动态偏移变形及移动平台算力受限三重技术挑战,提出基于Swin Transformer的输电通道外破目标快速识别方法。采用物理尺度感知机制强化小目标响应,构建可变形特征对齐模块校正... 针对输电通道外力破坏目标识别中低对比度特征提取困难、导线动态偏移变形及移动平台算力受限三重技术挑战,提出基于Swin Transformer的输电通道外破目标快速识别方法。采用物理尺度感知机制强化小目标响应,构建可变形特征对齐模块校正导线弧垂空间偏移,设计分组空洞卷积架构覆盖多尺度目标特征;结合通道剪枝与算子融合技术实现硬件加速,融合几何约束损失函数建立三维空间安全约束。实验结果表明:所提方法在Jetson AGX Xavier平台实现单帧42.3 ms实时处理速度,定位准确率达100%;较YOLOv5方法时延降低38.2%,较Faster R-CNN方法准确率提升10个百分点。由此得出,所提方法能为输电通道外破目标识别提供高精度与强实时性的解决方案。 展开更多
关键词 特征对齐 分组空洞卷积 多尺度目标 通道剪枝 算子融合 外破目标识别
暂未订购 下载PDF
基于组卷积和膨胀卷积的轻量注意力模块 认领 引用
14
作者 张恩淘 郝晓丽 牛保宁 《计算机工程与设计》 北大核心 2025年第2期493-499,共7页
为解决目前的注意力模块中参数量大、通道压缩导致信息丢失、空间信息学习不充分的缺点,提出一种基于组卷积、通道清洗和膨胀卷积的轻量注意力模块。采取组卷积和通道清洗的方式学习通道权重,能够在不压缩通道的前提下减少大量参数,使... 为解决目前的注意力模块中参数量大、通道压缩导致信息丢失、空间信息学习不充分的缺点,提出一种基于组卷积、通道清洗和膨胀卷积的轻量注意力模块。采取组卷积和通道清洗的方式学习通道权重,能够在不压缩通道的前提下减少大量参数,使不同组之间产生交互,充分学习通道信息。采取连续的膨胀卷积,合理设置膨胀率充分且均衡的学习空间信息。通过CIFAR100和VOC 2007+2012数据集对所提模块在图像分类和目标检测中进行实验,验证其能够在较少的花费下带来较大的提升。 展开更多
关键词 深度学习 卷积神经网络 注意力机制 组卷积 膨胀卷积 图像分类 目标检测
暂未订购 下载PDF
自适应感受野网络的行人重识别 认领 引用 被引量：12
15
作者 王松 纪鹏 +2 位作者 张云洲 朱尚栋 暴吉宁 《控制与决策》 EI CSCD 北大核心 2022年第1期119-126,共8页
行人重识别通常删除特征提取网络中的最后一个空间下采样操作,以增加最后输出特征图的分辨率,保留更多的细粒度特征.然而,这种操作会大幅减小神经网络的感受野,而更大的感受野可以为行人重识别提供更多的上下文信息.同时,在实际的视觉... 行人重识别通常删除特征提取网络中的最后一个空间下采样操作,以增加最后输出特征图的分辨率,保留更多的细粒度特征.然而,这种操作会大幅减小神经网络的感受野,而更大的感受野可以为行人重识别提供更多的上下文信息.同时,在实际的视觉皮层中,相同区域的神经元的感受野是不同的,但当前行人重识别网络的设计大多忽视了这一点.为了解决上述问题,提出一种新颖的自适应感受野网络.网络的设计受启发于生物的视觉系统,通过在多分支网络上设置不同大小的感受野,结合注意力机制让网络自行选择合适的感受野特征,从而实现网络感受野的自适应,并且采用分组卷积使得自适应感受野模块更加轻量级.同时在各个分支利用空洞卷积增大感受野,补偿删除最后下采样操作所减少的网络感受野.在公开的大规模数据集上进行实验,实验结果表明,所提出的算法相比于基线方法有显著的提升,当使用ResNet-50作为特征提取网络时,在DukeMTMC-reID、Market-1501数据集上的Rank-1和mAP分别达到89.2%和76.0%、95.2%和87.2%.与现有方法相比,所提出算法在精度上有明显的提升. 展开更多
关键词 行人重识别 深度学习 自适应感受野 注意力机制 空洞卷积 分组卷积
暂未订购 下载PDF
基于改进知识一致性注意力的图像修复算法 认领 引用 被引量：7
16
作者 李海燕 尹浩林 +1 位作者 钟杏苑 张榆锋 《华中科技大学学报（自然科学版）》 EI CAS CSCD 北大核心 2023年第9期110-117,共8页
为有效解决修复大面积不规则洞孔出现的纹理模糊、结构失真等问题,提出了基于改进知识一致性注意力机制图像修复算法.首先使用部分卷积对待修复图像进行处理,随后将处理的特征图送入包含混合空洞卷积(HDC)与改进知识一致性注意力机制(K... 为有效解决修复大面积不规则洞孔出现的纹理模糊、结构失真等问题,提出了基于改进知识一致性注意力机制图像修复算法.首先使用部分卷积对待修复图像进行处理,随后将处理的特征图送入包含混合空洞卷积(HDC)与改进知识一致性注意力机制(KCA)的特征推理模块.推理完成后将输出特征图输入至部分卷积与特征推理模块进行循环推理,逐步提升网络的修复能力,循环完成后对输出图像进行特征合并.最后将合并特征图进行去残差瓶颈层以增强修复图像的结构完整性.提出模型使用组归一化方式(GN)加快损失函数收敛速度.在公开数据集上验证提出算法的性能,主客观实验结果表明:提出算法能有效修复大面积连续不规则区域,能够较好地避免修复失真,其峰值信噪比和结构相似度及运算速度优于对比算法. 展开更多
关键词 图像修复 混合空洞卷积 不规则洞孔 注意力机制 组归一化
暂未订购 下载PDF
面向舱室声学环境的深度时域语音增强网络 认领 引用 被引量：4
17
作者 张琳 王海涛 +2 位作者 杨爽 曾向阳 陈克安 《声学学报》 EI CAS CSCD 北大核心 2023年第4期890-900,共11页
针对舱室环境单通道语音增强问题,设计了一种联合并行空洞卷积与分组卷积的深度时域语音增强网络。该网络以经典卷积时域音频分离网络为基础,在增强层设计中通过不同膨胀因子执行两路并行的空洞卷积操作,实现对长时信号的处理以更多地... 针对舱室环境单通道语音增强问题,设计了一种联合并行空洞卷积与分组卷积的深度时域语音增强网络。该网络以经典卷积时域音频分离网络为基础,在增强层设计中通过不同膨胀因子执行两路并行的空洞卷积操作,实现对长时信号的处理以更多地提取信号包络所包含的低频信息并抑制噪声混响所带来的时延问题,同时保留了局部的语音细节信息,提高对波形中所包含语音及背景噪声谐波信息的提取准确度;另外,利用分组卷积降低并行卷积操作所导致的网络规模扩大,使网络在具有良好增强效果的同时能够保持较小的网络规模及运算复杂度。以多类飞机舱室噪声为数据基础的实验表明,所设计的网络模块相较于基线网络提升了客观评价指标值,与现有其他常用网络的比较结果表明此方法在舱室环境的数据条件下可获得更好的主客观语音增强评价指标,且在高噪声级的线谱及窄带处具有更低的失真度。 展开更多
关键词 舱室环境 单通道语音增强 深度网络 并行空洞卷积 分组卷积
暂未订购 下载PDF
基于特征重用和膨胀卷积的遥感图像舰船检测 认领 引用 被引量：3
18
作者 曲海成 李瑞柯 +1 位作者 王蒙 单以盟 《智能系统学报》 CSCD 北大核心 2024年第5期1298-1308,共11页
在光学遥感图像中,港口内的舰船目标通常处于密集的船只群中,并受到周围环境的干扰和遮挡,如集装箱、车辆等。为了进一步提高现有舰船目标检测算法的精度和泛化性能,提出了一种基于特征重用和膨胀卷积的遥感图像舰船检测算法。首先构建... 在光学遥感图像中,港口内的舰船目标通常处于密集的船只群中,并受到周围环境的干扰和遮挡,如集装箱、车辆等。为了进一步提高现有舰船目标检测算法的精度和泛化性能,提出了一种基于特征重用和膨胀卷积的遥感图像舰船检测算法。首先构建了基于分组卷积和拆分注意力的残差块来提取特征,同时嵌入可变形卷积提取更加符合舰船尺度变化的特征;接着,构造了多尺度感受野模块,通过并行提取多尺度特征后再进行融合来减少信息损失;最后,在原有特征金字塔的基础上构建了一条自底向上的特征重用聚合路径以提高特征表示能力。在大型遥感数据集DOTA和舰船数据集HRSC2016上进行实验,实验结果表明,所提方法能够有效缓解舰船目标漏检和误检问题,提高了遥感图像舰船目标检测的精度。 展开更多
关键词 遥感图像 舰船检测 特征重用 膨胀卷积 拆分注意力 分组卷积 特征金字塔 可变形卷积
暂未订购 下载PDF
基于深度学习的门机抓斗检测方法 认领 引用 被引量：3
19
作者 张文明 刘向阳 +1 位作者 李海滨 李雅倩 《光电工程》 CAS CSCD 北大核心 2021年第1期14-23,共10页
在港口门机抓斗装卸干散货的作业过程中,人眼观察无法精确判断抓斗所在位置,会带来工作效率低下及安全性等问题。为解决该问题首次提出了一种基于深度学习的门机抓斗检测方法。利用改进的深度卷积神经网络YOLOv3-tiny对抓斗数据集进行... 在港口门机抓斗装卸干散货的作业过程中,人眼观察无法精确判断抓斗所在位置,会带来工作效率低下及安全性等问题。为解决该问题首次提出了一种基于深度学习的门机抓斗检测方法。利用改进的深度卷积神经网络YOLOv3-tiny对抓斗数据集进行训练及测试,进而学习其内部特征表示。实验结果表明,基于深度学习的门机抓斗检测方法可实现门机抓斗检测速度每秒45帧,召回率高达95.78%,在很好满足检测实时性与准确性的同时,提高了工业现场作业的安全性及效率。 展开更多
关键词 抓斗检测 深度学习 YOLOv3-tiny 空间金字塔池化 反转残差组 空洞卷积
暂未订购 下载PDF
基于多任务深度学习的快速人像自动抠图 认领 引用 被引量：5
20
作者 许征波 杨煜俊 《武汉大学学报（工学版）》 CAS CSCD 北大核心 2020年第8期740-745,752,共6页
针对大多数人像抠图存在时效性低、需要人工标注三分图和依赖颜色作为主要依据而导致精度难提高的问题,提出一种基于多任务学习的神经网络的快速人像自动抠图算法。该方法首先对图像的三分图进行学习预测,并将得到的信息反馈至网络后去... 针对大多数人像抠图存在时效性低、需要人工标注三分图和依赖颜色作为主要依据而导致精度难提高的问题,提出一种基于多任务学习的神经网络的快速人像自动抠图算法。该方法首先对图像的三分图进行学习预测,并将得到的信息反馈至网络后去学习预测图像的α值,网络结构采用编码器-解码器的方式,编码器部分使用深度可分离残差卷积做特征提取,和多组空洞卷积并联组合使得网络拥有足够的感受野;解码部分使用双线性加性上采样使特征图逐步恢复至原图大小,另外使用跳跃连接层将编码和解码部分相连接;使用公开数据库作为测试集,与Deeplab加文献[3]算法和DAPM算法进行对比,实验结果表明在运行时间、SAD、MSE和Gradient评价指标上优于对比算法。 展开更多
关键词 人像抠图 可分离卷积 空洞卷积 双线性加性 组归一化
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈