检索结果-内蒙古大学图书馆

Information Science, parallel and distributed Systems (ISPDS), International conference on

作者： Chengjia Jiang Tao Wang Sien Li Jinyang Wang Shirui Wang Antonios Antoniou Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China The Key Laboratory of Cognitive Computing and Intelligent Information Processing Fujian Education Institutions Wuyi University Wuyishan China College of Computer and Data Science Fuzhou University Fuzhou China Department of Computer Science and Engineering European University Cyprus Nicosia Cyprus

We address the problem of learning new classes for semantic segmentation models from few examples, which is challenging because of the following two reasons. Firstly, it is difficult to learn from limited novel data to capture the underlying class distribution. Secondly, it is challenging to retain knowledge for existing classes and to avoid catastrophic forgetting. For learning from limited data, we propose a pseudo-labeling strategy to augment the few-shot training annotations in order to learn novel classes more effectively. Given only one or a few images labeled with the novel classes and a much larger set of unlabeled images, we transfer the knowledge from labeled images to unlabeled images with a coarse-to-fine pseudo-labeling approach in two steps. Specifically, we first match each labeled image to its nearest neighbors in the unlabeled image set at the scene level, in order to obtain images with a similar scene layout. This is followed by obtaining pseudo-labels within this neighborhood by applying classifiers learned on the few-shot annotations. In addition, we use knowledge distillation on both labeled and unlabeled data to retain knowledge on existing classes. We integrate the above steps into a single convolutional neural network with a unified learning objective. Extensive experiments on the Cityscapes and KITTI datasets validate the efficacy of the proposed approach in the self-driving domain. Code is available from https://***/ChasonJiang/FSCILSS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Lightweight Bimodal Rail Surface Defect Detection Method: parallel-YOLOv4-Tiny 5

Lightweight Bimodal Rail Surface Defect Detection Method: Pa...

引用

5th International conference on Video and image processing (ICVIP)

作者： Zheng, Jiajun Han, Qiang Wang, Le Wang, Shengchun Zhang, Zhiyong Wang, Luping Wang, Liang Sun Yat Sen Univ Sch Elect & Commun Engn Guangzhou Peoples R China China Acad Railway Sci Corp Ltd Beijing Peoples R China

ISBN: (纸本)9781450385893

Rail defect has been harmful to the safety of railway operation for a long time. At present, there is an urgent need for a fast and high-precision rail surface defect detection method which can be applied to comprehensive inspection vehicles. In this paper, we propose a lightweight Bimodal Rail Surface Defect Detection Method, called parallel-YOLOv4-Tiny, for bimodal rail surface defect images. We design a parallel feature processing strategy for bimodal image feature extraction in parallel-YOLOv4-Tiny. A series of experiments show that parallel-YOLOv4-Tiny with CIOU loss function can achieve a mAP of 92.07 at 88 FPS on a single GPU. parallel-YOLOv4-Tiny has a much better performance than other original YOLOv4-Tiny methods, which shows the validity and advancement of parallel-YOLOv4-Tiny. parallel-YOLOv4-Tiny can meet the practical application requirements of high-speed railways and improve the efficiency of daily railway patrol inspection.

关键词： lightweight network bimodal rail surface defect detection parallel-YOLOv4-Tiny

来源：评论

学校读者我要写书评

暂无评论

PI-Trans: parallel-Convmlp and Implicit-Transformation Based Gan for Cross-View image Translation

PI-Trans: Parallel-Convmlp and Implicit-Transformation Based...

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Bin Ren Hao Tang Yiming Wang Xia Li Wei Wang Mcu Sebe University of Pisa University of Trento ETH Zurich FBK Beijing Jiaotong University

For semantic-guided cross-view image translation, it is crucial to learn where to sample pixels from the source view image and where to reallocate them guided by the target view semantic map, especially when there is little overlap or drastic view difference between the source and target images. Hence, one not only needs to encode the long- range dependencies among pixels in both the source view image and target view semantic map but also needs to translate these learned dependencies. To this end, we propose a novel generative adversarial network, PI-Trans, which mainly consists of a novel parallel-ConvMLP module and an Implicit Transformation module at multiple semantic levels. Extensive experimental results show that PI-Trans achieves the best qualitative and quantitative performance by a large margin compared to the state-of-the-art methods on two challenging datasets. The source code is available at https://***/Amazingren/PI-Trans.

关键词： Source coding Semantics Signal processing Maintenance engineering Generative adversarial networks Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

RGBT Tracking via Multi-Adapter Network with Hierarchical Divergence Loss

引用

IEEE TRANSACTIONS ON image processing 2021年 30卷 5613-5625页

作者： Lu, Andong Li, Chenglong Yan, Yuqing Tang, Jin Luo, Bin Anhui Univ Sch Artificial Intelligence Informat Mat & Intelligent Sensing Lab Anhui Prov Anhui Prov Key Lab Multimodal Cognit Computat Hefei 230601 Peoples R China

RGBT tracking has attracted increasing attention since RGB and thermal infrared data have strong complementary advantages, which could make trackers all-day and all-weather work. Existing works usually focus on extracting modality-shared or modality-specific information, but the potentials of these two cues are not well explored and exploited in RGBT tracking. In this paper, we propose a novel multi-adapter network to jointly perform modality-shared, modality-specific and instance-aware target representation learning for RGBT tracking. To this end, we design three kinds of adapters within an end-to-end deep learning framework. In specific, we use the modified VGG-M as the generality adapter to extract the modality-shared target representations. To extract the modality-specific features while reducing the computational complexity, we design a modality adapter, which adds a small block to the generality adapter in each layer and each modality in a parallel manner. Such a design could learn multilevel modality-specific representations with a modest number of parameters as the vast majority of parameters are shared with the generality adapter. We also design instance adapter to capture the appearance properties and temporal variations of a certain target. Moreover, to enhance the shared and specific features, we employ the loss of multiple kernel maximum mean discrepancy to measure the distribution divergence of different modal features and integrate it into each layer for more robust representation learning. Extensive experiments on two RGBT tracking benchmark datasets demonstrate the outstanding performance of the proposed tracker against the state-of-the-art methods.

关键词： Feature extraction Target tracking Data mining Mobile computing Adaptation models Ad hoc networks Kernel RGBT tracking multiple adapters parallel design hierarchical divergence loss representation learning

来源：评论

学校读者我要写书评

暂无评论

Neural cover selection for image steganography 24

Neural cover selection for image steganography

引用

Proceedings of the 38th International conference on Neural Information processing Systems

作者： Karl Chahine Hyeji Kim Department of Electrical and Computer Engineering University of Texas at Austin Austin TX

ISBN: (纸本)9798331314385

In steganography, selecting an optimal cover image—referred to as cover selection—is pivotal for effective message concealment. Traditional methods have typically employed exhaustive searches to identify images that conform to specific perceptual or complexity metrics. However, the relationship between these metrics and the actual message hiding efficacy of an image is unclear, often yielding less-than-ideal steganographic outcomes. Inspired by recent advancements in generative models, we introduce a novel cover selection framework, which involves optimizing within the latent space of pretrained generative models to identify the most suitable cover images, distinguishing itself from traditional exhaustive search methods. Our method shows significant advantages in message recovery and image quality. We also conduct an information-theoretic analysis of the generated cover images, revealing that message hiding predominantly occurs in low-variance pixels, reflecting the waterfilling algorithm's principles in parallel Gaussian channels. Our code can be found at https://***/karlchahine/Neural-Cover-Selection-for-image-Steganography.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic DNN Decomposition for Lossless Synergistic Inference 41

Dynamic DNN Decomposition for Lossless Synergistic Inference

引用

IEEE 41st International conference on distributed Computing Systems (ICDCS)

作者： Zhang, Beibei Xiang, Tian Zhang, Hongxuan Li, Te Zhu, Shigiang Gu, Jianjun Zhejiang Lab Intelligent Robot Res Ctr Hangzhou Peoples R China

ISBN: (纸本)9781665449328

Deep neural networks (DNNs) sustain high performance in today's data processing applications. DNN inference is resource-intensive thus is difficult to fit into a mobile device. To solve this problem, recent advances unleash DNN services using the edge computing paradigm. The existing approaches split a DNN into two parts and deploy the two partitions to computation nodes at two edge computing tiers. Nonetheless, these methods overlook collaborative device-edge-cloud computation resources. Besides, previous algorithms demand the whole DNN re-partitioning to adapt to computation resource changes and network dynamics. Moreover, for resource-demanding convolutional layers, prior works do not give a parallel processing strategy without loss of accuracy at the edge side. To tackle these issues, we propose D-3, a dynamic DNN decomposition system for synergistic inference without precision loss. The proposed system introduces a heuristic algorithm named horizontal partition algorithm to split a DNN into three parts. The algorithm partially adjust the partitions at run time according to processing time and network conditions. At the edge side, a vertical separation module separates feature maps into tiles that can be independently run on different edge nodes in parallel. Extensive quantitative evaluation of five popular DNNs illustrates that D-3 outperforms the stateof-the-art counterparts up to 3.4X in end-to-end DNN inference time and reduces backbone network communication overhead up to 3.68X.

关键词： distributed computing Edge computing DNN inference acceleration

来源：评论

学校读者我要写书评

暂无评论

Traffic processing and Fingerprint Generation for Smart Home Device Event

Traffic Processing and Fingerprint Generation for Smart Home...

引用

International conference on parallel and distributed Systems (ICPADS)

作者： Yunhao Yao Jiahui Hou Sijia Zhang Zhengyuan Xu Xiang-Yang Li School of Computer Science and Technology USTC China School of Information Science and Technology USTC China

Recent studies show that smart home devices are vulnerable to passive network observers, referred to as adversaries. An adversary can use mobile devices as a sniffer to infer device events (e.g., a door is opened/closed) even through encrypted WiFi traffic. However, to obtain high event identification accuracy, existing works heavily rely on either machine learning (ML) or large traffic feature sizes, which results in a costly retraining or pairing process. In this paper, we generate an event traffic fingerprint and propose an event identification method with good extensibility. To address the interference of network fluctuations and unrelated traffic, we filter all redundant and event-unrelated packets and extract event packet sequences based on time interval. After processing, we generate a representative packet-level fingerprint for each event and identify the event based on fingerprint matching. The precision and recall of event identification reach 96.77% and 92.31% on average. Our traffic processing method can work as an add-on to existing ML-based event inference methods, which leads to at least 12% increase on the accuracy.

关键词： Performance evaluation Wide area networks Passive networks Fluctuations Smart homes Machine learning Interference

来源：评论

学校读者我要写书评

暂无评论

DFTS2: Deep Feature Transmission Simulation for Collaborative Intelligence

DFTS2: Deep Feature Transmission Simulation for Collaborativ...

引用

IEEE International conference on Visual Communications and image processing (VCIP) - Visual Communications in the Era of AI and Limited Resources

作者： Dhondea, Ashiv Cohen, Robert A. Bajic, Ivan, V Simon Fraser Univ Sch Engn Sci Burnaby BC V5A 1S6 Canada

ISBN: (纸本)9781728185514

In edge-cloud collaborative intelligence (CI), an unreliable transmission channel exists in the information path of the Al model performing the inference. It is important to be able to simulate the performance of the CI system across an imperfect channel in order to understand system behavior and develop appropriate error control strategies. In this paper we present a simulation framework called DFTS2, which enables researchers to define the components of the CI system in TensorFlow 2, select a packet-based channel model with various parameters, and simulate system behavior under various channel conditions and error/loss control strategies. Using DFTS2, we also present the most comprehensive study to date of the packet loss concealment methods for collaborative image classification models.

关键词： Collaborative intelligence distributed AI feature transmission error resilience packet loss

来源：评论

学校读者我要写书评

暂无评论

Stealing Secrecy from Outside: A Novel Gradient Inversion Attack in Federated Learning

Stealing Secrecy from Outside: A Novel Gradient Inversion At...

引用

International conference on parallel and distributed Systems (ICPADS)

作者： Chuan Zhang Haotian Liang Youqi Li Tong Wu Liehuang Zhu Weiting Zhang School of Cyberspace Science and Technology Beijing Institute of Technology Beijing China Yangtze Delta Region Academy of Beijing Institute of Technology Jiaxing China School of Electronic and Information Engineering Beijing Jiaotong University Beijing China

Knowing model parameters has been regarded as a vital factor for recovering sensitive information from the gradients in federated learning. But is it safe to use federated learning when the model parameters are unavailable for adversaries, i.e., external adversaries’ In this paper, we answer this question by proposing a novel gradient inversion attack. Speciffically, we observe a widely ignored fact in federated learning that the participants’ gradient data are usually transmitted via the intermediary node. Based on this fact, we show that an external adversary is able to recover the private input from the gradients, even if it does not have the model parameters. Through extensive experiments based on several real-world datasets, we demonstrate that our proposed new attack can recover the input with pixelwise accuracy and feasible efficiency.

关键词： image resolution Federated learning Data models Security image reconstruction Finite difference methods

来源：评论

学校读者我要写书评

暂无评论

Deep Steganography based on CBAM

Deep Steganography based on CBAM

引用

Robotics, Artificial Intelligence and Intelligent Control (RAIIC), International conference on

作者： Qian Dang Peng Luo School of Cryptography Engineering Engineering University of PAP Xi’an China

ISBN: (数字)9798350352627

ISBN: (纸本)9798350352634

Deep steganography techniques, as an effective means of secure information transmission, are increasingly attracting attention. To solve the low visual performance of current encoder-decoder based deep steganography methods, this paper proposes the attStega which incorporate CBAM (Convolutional Block Attention Module) after each convolutional block in the decoder (comprising convolution, batch normalization, and LeakyReLU), which embed messages adaptively distributed within the cover image. Experimental results demonstrate that, while maintaining the embedding capacity and security, the visual effect of steganography has been improved.

关键词： image quality Steganography Attention mechanisms Convolution Information processing Visual effects Decoding

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：