检索结果-内蒙古大学图书馆

FastHand: Fast monocular hand pose estimation on embedded systems

JOURNAL OF SYSTEMS ARCHITECTURE 2022年 122卷

作者： An, Shan Zhang, Xiajie Wei, Dong Zhu, Haogang Yang, Jianyu Tsintotas, Konstantinos A. Beihang Univ Sch Comp Sci & Engn Beijing 100191 Peoples R China JD COM Inc Tech & Data Ctr Beijing 100108 Peoples R China Soochow Univ Sch Rail Transportat Suzhou 215006 Peoples R China Democritus Univ Thrace Dept Prod & Management Engn Xanthi 67132 Greece

Hand pose estimation is a fundamental task in many human-robot interaction-related applications. However, previous approaches suffer from unsatisfying hand landmark predictions in real-world scenes and high computation burden. This paper proposes a fast and accurate framework for hand pose estimation, dubbed as "FastHand". Using a lightweight encoder-decoder network architecture, FastHand fulfills the requirements of practical applications running on embedded devices. The encoder consists of deep layers with a small number of parameters, while the decoder uses spatial location information to obtain more accurate results. The evaluation took place on two publicly available datasets demonstrating the improved performance of the proposed pipeline compared to other state-of-the-art approaches. FastHand offers high accuracy scores while reaching a speed of 25 frames per second on an NVIDIA Jetson TX2 graphics processing unit.

关键词： Hand pose estimation Landmark localization Hand detection encoder-decoder network Heatmap regression

来源：评论

学校读者我要写书评

暂无评论

Black-box attack against GAN-generated image detector with contrastive perturbation

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2023年第1期124卷

作者： Lou, Zijie Cao, Gang Lin, Man Commun Univ China State Key Lab Media Convergence & Commun Beijing 100024 Peoples R China Commun Univ China Sch Comp & Cyber Sci Beijing 100024 Peoples R China

The emergence of visually realistic GAN-generated facial images has raised concerns regarding potential misuse. In response, effective forensic algorithms have been developed to detect such synthetic images in recent years. However, the vulnerability of such forensic detectors to adversarial attacks remains an important issue that requires further investigation. In this paper, we propose a new black-box attack method against GAN-generated image detectors. It involves contrastive learning strategy to train an encoder-decoder anti -forensic network with a contrastive loss function. GAN-generated and corresponding simulated real images are constructed as positive and negative samples, respectively. By leveraging the trained attack model, we can apply imperceptible perturbation to input synthetic images for removing GAN fingerprint to some extent. GAN-generated image detectors may be deceived consequently. Extensive experimental results demonstrate that the proposed attack effectively reduces the accuracy of three state-of-the-art detectors on six popular GANs, while also achieving high visual quality of the attacked images. The source code will be available at https://***/ZXMMD/BAttGAND.

关键词： Black-box attack Anti-forensic GAN-generated image detector GAN fingerprint encoder-decoder network Contrastive perturbation

来源：评论

学校读者我要写书评

暂无评论

LDPNet: A Lightweight Densely Connected Pyramid network for Real-Time Semantic Segmentation

引用

IEEE ACCESS 2020年 8卷 212647-212658页

作者： Hu, Xuegang Jing, Liyuan Chongqing Univ Posts & Telecommun Sch Commun & Informat Engn Chongqing 400065 Peoples R China Chongqing Univ Posts & Telecommun Multimedia Commun Res Lab Chongqing 400065 Peoples R China

A deep convolutional neural network has been widely used in image semantic segmentation in recent years, its deployment on mobile terminals, however is limited by its high computational costs. Given the slow inference speed and large memory usage of deep convolutional neural networks, we propose a lightweight and densely connected pyramid network (LDPNet) for real-time semantic segmentation. Firstly, a densely connected atrous pyramid (DCAP) module is constructed in the encoding process to extract multi-scale context information for forwarding propagation, strengthen the reuse of features, and offset the spatial information lost in the down-sampling process of the feature map. Secondly, a cross-fusion (CF) module embedded in each other during the decoding process is proposed, which uses high-level semantic features to effectively guide the fusion of low-level spatial details while strengthening context information. Our network is tested on two complex urban road scene data sets. Among them, experiments on the Cityscapes data set show that our structure has 87 frames per second (FPS) on a single NVIDIA GTX1080Ti GPU. The Mean Intersection over Union (mIoU) reaches 71.1%, and the parameter is only 0.8M. Compared with the existing similar networks, the new system achieves a state-of-the-art trade-off between efficiency and accuracy.

关键词： Convolution Semantics Image segmentation Real-time systems Feature extraction Kernel Computational modeling Deep convolutional neural network lightweight network encoder-decoder network atrous pyramid module real-time semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

CloudSwinNet: A hybrid CNN-transformer framework for ground-based cloud images fine-grained segmentation

引用

ENERGY 2024年 309卷

作者： Shi, Chaojun Su, Zibo Zhang, Ke Xie, Xiongbin Zhang, Xiaoyun North China Elect Power Univ Dept Elect Commun Engn Baoding 071003 Hebei Peoples R China North China Elect Power Univ Hebei Key Lab Power Internet Things Technol Baoding 071003 Hebei Peoples R China

Solar irradiance is the main factor affecting the output of a photovoltaic (PV) power station. The dominant role of ground-based clouds on the variation of direct solar radiation in the whole sky. Ground-based cloud segmentation plays a crucial role in photovoltaic power generation prediction. Despite advancements, current cloud segmentation methods fail to meet the requirements of this application. While convolutional neural networks demonstrate impressive segmentation capabilities in ground-based cloud segmentation tasks, their inherent limitations hinder further performance enhancement. Hence, this paper introduces CloudSwinNet, a hybrid CNNTransformer framework for ground-based cloud images fine-grained segmentation. CloudSwinNet leverages concepts from convolutional neural networks, including stepwise downsampling, local convolution, and skip connections. To further explore the fine-grained features in the ground-based cloud images, we incorporates the Fine-grained Feature Fusion Module (Fg-FFM) in encoder structure, while the jump connection structure integrates the GloRe spatial graph inference module. These additions enable comprehensive learning of multi-scale and long-range dependencies. We conducted extensive experiments on the fine-grained ground-based cloud dataset, demonstrating that CloudSwinNet outperforms six semantic segmentation networks in both qualitative and quantitative evaluations. The results of ablation experiments prove the effectiveness of the module introduced in this paper.

关键词： Photovoltaic power generation prediction Ground-based cloud images segmentation encoder-decoder network Swin-Transformer Feature fusion module

来源：评论

学校读者我要写书评

暂无评论

Cascaded deep convolutional encoder-decoder neural networks for efficient liver tumor segmentation

引用

MEDICAL HYPOTHESES 2020年 134卷 109431-109431页

作者： Budak, Umit Guo, Yanhui Tanyildizi, Erkan Sengur, Abdulkadir Bitlis Eren Univ Engn Fac Elect & Elect Engn Dept Bitlis Turkey Univ Illinois Dept Comp Sci Springfield IL 62703 USA Firat Univ Technol Fac Dept Elect & Elect Engn Elazig Turkey

Liver and hepatic tumor segmentation remains a challenging problem in Computer Tomography (CT) images analysis due to its shape variation and vague boundary. The general hypothesis says that deep learning methods produce improved results on medical image segmentation. This paper formulates the segmentation of liver tumor in CT abdominal images as a classification problem, and then solves it using a cascaded classifier framework based on deep convolutional neural networks. Two deep encoder-decoder convolutional neural networks (EDCNN) were constructed and trained to cascade segments of both the liver and lesions in CT images with limited image quantity. In other words, an EDCNN segments the liver image as the input for the training of a second EDCNN. The second EDCNN then segments the tumor regions within the liver ROI regions as predicted by the first EDCNN. Segmenting the hepatic tumor inside the liver ROI also significantly reduces false-positives. The proposed model was then tested using a public dataset (3DIRCADb), and several metrics were used in order to quantitatively evaluate its performance. The proposed method produced an average DICE score of 95.22% for the test set of CT images. The proposed method was then compared with some of the existing methods. The experimental results demonstrated that the proposed EDCNN achieved improved performance in segmentation accuracy over some existing methods.

关键词： Cascaded network Convolutional neural network encoder-decoder network Liver segmentation

来源：评论

学校读者我要写书评

暂无评论

LFFNet: lightweight feature-enhanced fusion network for real-time semantic segmentation of road scenes

引用

PATTERN ANALYSIS AND APPLICATIONS 2024年第1期27卷 27-27页

作者： Hu, Xuegang Feng, Jing Gong, Juelin Chongqing Univ Posts & Telecommun Sch Commun & Informat Engn Chongqing 400065 Peoples R China Chongqing Univ Posts & Telecommun Chongqing Key Lab Signal & Informat Proc Chongqing 400065 Peoples R China

Deep neural networks have significantly improved semantic segmentation, but their great performance frequently comes at the expense of expensive computation and protracted inference times, which fall short of the exacting standards of real-world applications. A lightweight feature-enhanced fusion network (LFFNet) for real-time semantic segmentation is proposed. LFFNet is a particular type of asymmetric encoder-decoder structure. In the encoder, A multi-dilation rate fusion module can guarantee the retention of local information while enlarging the appropriate field in the encoder section, which resolves the issue of insufficient feature extraction caused by the variability of target size. In the decoder, different decoding modules are designed for spatial information and semantic information. The attentional feature enhancement module takes advantage of the attention mechanism to feature-optimize the contextual information of the high-level output, and the lightweight multi-scale feature fusion module fuses the features from various stages to aggregate more spatial detail information and contextual semantic information. The experimental findings demonstrate that LFFNet achieves 72.1% mIoU and 67.0% mIoU on Cityscapes and Camvid datasets at 102 FPS and 244 FPS, respectively, with only 0.63M parameters. Note that there is neither pretraining nor pre-processing. Our model can achieve superior segmentation performance with fewer parameters and less computation compared to existing networks.

关键词： Real-time semantic segmentation Attention mechanism encoder-decoder network Feature fusion

来源：评论

学校读者我要写书评

暂无评论

EffResUNet: encoder decoder Architecture for Cloud-Type Segmentation

引用

BIG DATA AND COGNITIVE COMPUTING 2022年第4期6卷 150页

作者： Nalwar, Sunveg Shah, Kunal Bidwe, Ranjeet Vasant Zope, Bhushan Mane, Deepak Jadhav, Veena Shaw, Kailash Pune Inst Comp Technol SCTRs Pune 411043 India Symbiosis Int Deemed Univ SIU Symbiosis Inst Technol SIT Pune 412115 India JSPMs Rajarshi Shahu Coll Engn Dept Comp Engn Pune 411033 India Bharati Vidyapeeth Deemed Univ Coll Engn Dept Comp Engn Pune 411043 India

Clouds play a vital role in Earth's water cycle and the energy balance of the climate system;understanding them and their composition is crucial in comprehending the Earth-atmosphere system. The dataset "Understanding Clouds from Satellite Images" contains cloud pattern images downloaded from NASA Worldview, captured by the satellites divided into four classes, labeled Fish, Flower, Gravel, and Sugar. Semantic segmentation, also known as semantic labeling, is a fundamental yet complex problem in remote sensing image interpretation of assigning pixel-by-pixel semantic class labels to a given picture. In this study, we propose a novel approach for the semantic segmentation of cloud patterns. We began our study with a simple convolutional neural network-based model. We worked our way up to a complex model consisting of a U-shaped encoder-decoder network, residual blocks, and an attention mechanism for efficient and accurate semantic segmentation. Being an architecture of the first of its kind, the model achieved an IoU score of 0.4239 and a Dice coefficient of 0.5557, both of which are improvements over the previous research conducted in this field.

关键词： semantic segmentation encoder-decoder network satellite images clouds

来源：评论

学校读者我要写书评

暂无评论

Generating Adversarial Examples with Image-To-Perturbation network

Generating Adversarial Examples with Image-To-Perturbation N...

引用

第三十九届中国控制会议

作者： Desheng Wang Weidong Jin Yunpu Wu School of Electrical Engineering Southwest Jiaotong University

Deep neural networks have been found to be easily misled by adversarial examples that are maliciously crafted by adding small perturbations. A variety of methods have been proposed to generate adversarial examples, but more efforts are needed to generate them with high perceptual quality and low computation costs. In this paper, we propose an adversarial attack method that uses a conditional encoder-decoder network named Image-To-Perturbation to generate adversarial perturbations in residual learning fashion. Image-To-Perturbation network can learn the mapping from clean images to according adversarial perturbations, once it is trained, it can generate perturbations for any examples efficiently. We test the proposed method on different target models using MNIST and CIFAR-10 datasets. The experimental results show that our model is easy to train and the generated adversarial examples are perceptually realistic and achieve high attack success rate.

关键词： Deep Neural networks Adversarial Examples encoder-decoder network

来源：评论

学校读者我要写书评

暂无评论

Multi-Stage Feature Reconstructed Semantic Segmentation of Construction Sites Under Multiple Weather Conditions 23

Multi-Stage Feature Reconstructed Semantic Segmentation of C...

引用

Proceedings of the 2023 International Conference on Power, Communication, Computing and networking Technologies

作者： Zhenguo Hou Zhongshan Zhang Weitao Yang Hao Luo Zheng Wang Chong Long China Construction Seventh Engineering Bureau Co. Ltd. China School of Computer and Information Hohai University China

ISBN: (纸本)9781450399951

Scene monitoring and automatic interpretation in construction site scenarios play a crucial role. However, the changes in illumination and weather conditions of construction sites have a significant impact on the imaging quality of visual cameras. The effectiveness of existing semantic segmentation methods is extremely decreased without considering this problem. To solve this issue, we propose the multi-stage feature reconstructed semantic segmentation method for all-day monitor in construction sites. This method aims to improve the robustness against changes in the external environment. Specifically, the self-calibrated module (SCM) is adopted to reconstruct the input image and calculate the effective encoded features. SCM is embedded into the network for several stages to reconstruct multi-level features. Then, the higher-level features are aggregated and enhanced along the channel dimensions, which could obtain more context information. The higher-level is gradually combined with lower-level detailed features for decoding process. The images in construction sites are randomly augmented from different aspects, which could supervise the training process to achieve robust semantic segmentation with the supplement of image reconstruction. The qualitative and quantitative experiments show that compared with several state-of-the-art semantic segmentation methods, the proposed method could better adapt to changes in the environmental conditions and achieve all-day segmentation.

关键词： Semantic segmentation construction site encoder-decoder network feature reconstruction

来源：评论

学校读者我要写书评

暂无评论

encoder-decoder-based image transformation approach for integrating multiple spatial forecasts

引用

MACHINE LEARNING WITH APPLICATIONS 2023年 12卷

作者： Hachiya, Hirotaka Masumoto, Yusuke Kudo, Atsushi Ueda, Naonori Wakayama Univ 930 Sakaedani Wakayama Wakayama 6408510 Japan RIKEN Ctr AIP Nihonbashi 1 Chome Mitsui Bldg15th Floor1-4-1 Ni Tokyo 1030027 Japan Japan Meteorol Agcy Numer Predict Dev Ctr 1-2 Nagamine Tsukuba Ibaraki 3050052 Japan

As the damage caused by heavy rainfall worsens, there is a growing demand for improved forecasts. One practical approach to address this issue is the linear integration of multiple existing forecasts, which allows for visualizing the contribution of each forecast at different locations. However, current methods such as arithmetic and Bayesian averages utilize a single weight shared across the entire space, making it difficult to account for local variations in importance. Additionally, while U -Net -based spatial forecasts have been proposed, they are limited to short-term predictions and do not facilitate the visualization of individual forecast contributions due to their non-linear processes. To overcome these challenges, we propose a new integration framework based on U -Net image transformation. This framework generates weight images that dynamically integrate forecasts based on both time and location. To effectively handle large and imbalanced precipitation data, we introduce novel extensions to the U -Net model. These extensions address heavily imbalanced precipitation data and enable position and time -dependent integration. Experimental results using real precipitation forecast data in Japan demonstrate that our proposed method outperforms existing integration methods.

关键词： Precipitation forecast Image-to-image transformation encoder-decoder network

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：