检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Wan, Yi Xie, Xianzhong Chen, Junfan Xie, Kunpeng Yi, Dezhi Lu, Ye Gai, Keke The College of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China Chongqing Haiyunjiexun Technology Co. Ltd Chongqing China The College of Computer Science Nankai University Tianjin300350 China The College of Cyber Science Nankai University Tianjin300350 China Tianjin Key Laboratory of Network and Data Security Technology Tianjin China State Key Laboratory of Processors ICT CAS Beijing China School of Cyberspace Science and Technology BIT Beijing China

Lightweight convolutional neural networks (CNNs) enable lower inference latency and data traffic, which are suitable for deployment on resource-constrained edge devices such as field-programmable gate arrays (FPGAs). However, repeated data access to off-chip synchronous dynamic random-access memory (SDRAM) is required during inference, which seriously results in a reduction in inference speed and system power efficiency. In this paper, we propose an adaptive dataflow scheduling method for lightweight CNN accelerator on FPGAs named ADS-CNN. The key idea of ADS-CNN is to efficiently utilize on-chip resources and reduce the amount of SDRAM access. To achieve the reuse of logical resources, we designed a time division multiplexing calculation engine in ADS-CNN. We developed a configurable module for the convolution controller, and the adaptability is reflected in the data reuse of different convolution layers, which reduces the off-chip access. Furthermore, we made rational use of on-chip memory blocks as buffers based on the configuration of different layers in lightweight CNNs. On the resource-constrained Intel CycloneV SoC 5CSEBA6 FPGA platform, we evaluated six common lightweight CNN models to demonstrate the performance advantages of ADS-CNN. The evaluation results indicate that, compared with accelerators using traditional tiling strategy dataflow, our ADS-CNN can achieve up to 1.29× acceleration gains with a 23.7% overall dataflow scale compression. © 2023, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Peer is Your Pillar: A data-unbalanced Conditional GANs for Few-shot Image Generation

arXiv

引用

arXiv 2023年

作者： Li, Ziqiang Wang, Chaoyue Rui, Xue Xue, Chao Leng, Jiaxu Li, Bin Big Data and Decision Lab University of Science and Technology of China China The University of Sydney Australia JD Explore Academic China School of computer science Chongqing University of Posts and Telecommunications China CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System China

Few-shot image generation aims to train generative models using a small number of training images. When there are few images available for training (e.g. 10 images), Learning From Scratch (LFS) methods often generate images that closely resemble the training data while Transfer Learning (TL) methods try to improve performance by leveraging prior knowledge from GANs pre-trained on large-scale datasets. However, current TL methods may not allow for sufficient control over the degree of knowledge preservation from the source model, making them unsuitable for setups where the source and target domains are not closely related. To address this, we propose a novel pipeline called Peer is your Pillar (PIP), which combines a target few-shot dataset with a peer dataset to create a data-unbalanced conditional generation. Our approach includes a class embedding method that separates the class space from the latent space, and we use a direction loss based on pre-trained CLIP to improve image diversity. Experiments on various few-shot datasets demonstrate the advancement of the proposed PIP, especially reduces the training requirements of few-shot image generation. © 2023, CC BY.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Proposal of a free-space-to-chip pipeline for transporting single atoms

arXiv

引用

arXiv 2023年

作者： Liu, Aiping Liu, Jiawei Kang, Zhanfei Chen, Guang-Jie Xu, Xin-Biao Ren, Xifeng Guo, Guang-Can Wang, Qin Zou, Chang-Ling Institute of Quantum Information and Technology Nanjing University of Posts and Telecommunications Nanjing210003 China CAS Key Laboratory of Quantum Information University of Science and Technology of China Hefei230026 China Broadband Wireless Communication and Sensor Network Technology Key Lab of Ministry of Education Nanjing University of Posts and Telecommunications Nanjing210003 China CAS Center for Excellence in Quantum Information and Quantum Physics University of Science and Technology of China Hefei230026 China

A free-space-to-chip pipeline is proposed to efficiently transport single atoms from a magneto-optical trap to an on-chip evanescent field trap. Due to the reflection of the dipole laser on the chip surface, the conventional conveyor belt approach can only transport atoms close to the chip surface but with a distance of about one wavelength, which prevents efficient interaction between the atom and the on-chip waveguide devices. Here, based on a two-layer photonic chip architecture, a diffraction beam of the integrated grating with an incident angle of the Brewster angle is utilized to realize free-space-to-chip atom pipeline. Numerical simulation verified that the reflection of the dipole laser is suppressed and that the atoms can be brought to the chip surface with a distance of only 100 nm. Therefore, the pipeline allows a smooth transport of atoms from free space to the evanescent field trap of waveguides and promises a reliable atom source for a hybrid photonic-atom chip. © 2023, CC BY.

关键词： Atoms

来源：评论

学校读者我要写书评

暂无评论

Unifying and Improving Graph Convolutional Neural networks with Wavelet Denoising Filters 23

Unifying and Improving Graph Convolutional Neural Networks w...

引用

2023 World Wide Web Conference, WWW 2023

作者： Wan, Liangtian Li, Xiaona Han, Huijin Yan, Xiaoran Sun, Lu Ning, Zhaolong Xia, Feng Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province School of Software Dalian University of Technology Dalian China Research Center of Big Data Intelligence Research Institute of Artificial Intelligence Zhejiang Lab Hangzhou China Department of Communication Engineering Institute of Information Science Technology Dalian Maritime University Dalian China School of Communication and Information Engineering Chongqing University of Posts and Telecommunications Chongqing China School of Computing Technologies Rmit University Melbourne Australia

ISBN: (纸本)9781450394161

Graph convolutional neural network (GCN) is a powerful deep learning framework for network data. However, variants of graph neural architectures can lead to drastically different performance on different tasks. Model comparison calls for a unifying framework with interpretability and principled experimental procedures. Based on the theories from graph signal processing (GSP), we show that GCN's capability is fundamentally limited by the uncertainty principle, and wavelets provide a controllable trade-off between local and global information. We adapt wavelet denoising filters to the graph domain, unifying popular variants of GCN under a common interpretable mathematical framework. Furthermore, we propose WaveThresh and WaveShrink which are novel GCN models based on proven denoising filters from the signal processing literature. Empirically, we evaluate our models and other popular GCNs under a more principled procedure and analyze how trade-offs between local and global graph signals can lead to better performance in different datasets. © 2023 ACM.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Secure Deduplication Against Frequency Analysis Attacks

Secure Deduplication Against Frequency Analysis Attacks

引用

International Conference on Mobile Ad-hoc and Sensor networks, MSN

作者： Hang Chen Guanxiong Ha Yuchen Chen Haoyu Ma Chunfu Jia College of Cyber Science Nankai University Tianjin China Tianjin Key Laboratory of Network and Data Security Technology Tianjin China Zhejiang Lab Hangzhou China The School of Cyber Engineering Xidian University Xi’an China

Message-locked Encryption (MLE) is the most common approach used in encrypted deduplication systems. However, the systems based on MLE are vulnerable to frequency analysis attacks, because MLE encrypts the identical plain texts into the identical ciphertexts, which is deterministic. The state-of-the- art defense scheme, which named TED, lacks key verification and uses a single key server to record frequency information. Once the key server is compromised, TED will be vulnerable to brute-force attacks. In addition, TED's key generation algorithm needs to be designed more exquisitely to strengthen protection, and its security indicator is not comprehensive. We propose SDAF, which supports key verification and enhanced protection against frequency analysis attacks. Based on chameleon hash, SDAF realizes key verification to prevent malicious key servers from generating fake encryption keys. In order to disturb the frequency information, SDAF introduces reservoir sample to generate uniformly distributed encryption keys, and uses multiple key servers, which interact with each other via multi-party PSI and rotate spontaneously to avoid the single point of failure. Moreover, a new indicator Kurtosis is pointed out to evaluate the security against frequency analysis attacks. We implement the prototypes of SDAF. The experiments of the real-world data sets show that, compared with the existing schemes, SDAF can better resist frequency analysis attacks with lower time overheads.

关键词： Maximum likelihood estimation Time-frequency analysis data privacy Art Prototypes Resists Reservoirs

来源：评论

学校读者我要写书评

暂无评论

Research on Knowledge Distillation of Generative Adversarial networks

Research on Knowledge Distillation of Generative Adversarial...

引用

data Compression Conference (DCC)

作者： Wei Wang Baohua Zhang Tao Cui Yimeng Chai Yue Li College of Computer Science KLMDASR Trusted AI System Lab Nankai University Tianjin China College of Computer Science Tianjin Key Lab of Network and Data Security Technology Nankai University Tianjin China NCMIS LSEC Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China

The compression of Generative Adversarial networks (GANs) has been an emerging study in recent years. However, conventional compression methods can hardly be applied to GANs due to the training process and optimization target of GANs are different from the traditional classification detection network. Inspired by the recent success of knowledge distillation, we condense the recent researches on them applied to particular GANs, i.e. WGAN and CGAN for special tasks into two strategies: Soft Target Only Strategy (STOS) and Inherited Hard Target Strategy (IHTS), and propose an novel Random Hard Target Strategy, namely RHTS. In RHTS, we take the student network generator loss as the hard target of knowledge distillation when the discriminator is fixed, and the output of the teacher network generator as the soft target to distill GANs. The experiments on image datasets (MNIST, CIFAR-10), and structured-data datasets (Australian Credit Approval dataset, Credit Approval data Set) show that STOS and IHTS are effective, and RHTS is the best. Such results are further proved on WGAN, WGAN-GP and LSGAN in order to demonstrate the better generalization ability of the strategies. Besides, the RHTS improve the stability of the GAN training process, where the performance and stability confirm the rationality of our design.

关键词： Training Knowledge engineering data compression Generative adversarial networks Generators Task analysis Optimization

来源：评论

学校读者我要写书评

暂无评论

Better Pseudo-label: Joint Domain-aware label and Dual-classifier for Semi-supervised Domain Generalization

arXiv

引用

arXiv 2021年

作者： Wang, Ruiqi Qi, Lei Shi, Yinghuan Gao, Yang State Key Laboratory for Novel Software Technology Nanjing University Nanjing China National Institute of Healthcare Data Science Nanjing University Nanjing China School of Computer Science and Engineering Key Lab of Computer Network and Information Integration Ministry of Education Southeast University Nanjing China

With the goal of directly generalizing trained model to unseen target domains, domain generalization (DG), a newly proposed learning paradigm, has attracted considerable attention. Previous DG models usually require a sufficient quantity of annotated samples from observed source domains during training. In this paper, we relax this requirement about full annotation and investigate semisupervised domain generalization (SSDG) where only one source domain is fully annotated along with the other domains totally unlabeled in the training process. With the challenges of tackling the domain gap between observed source domains and predicting unseen target domains, we propose a novel deep framework via joint domain-aware labels and dual-classifier to produce high-quality pseudo-labels. Concretely, to predict accurate pseudo-labels under domain shift, a domain-aware pseudo-labeling module is developed. Also, considering inconsistent goals between generalization and pseudo-labeling: former prevents overfitting on all source domains while latter might overfit the unlabeled source domains for high accuracy, we employ a dual-classifier to independently perform pseudo-labeling and domain generalization in the training process. When accurate pseudo-labels are generated for unlabeled source domains, the domain mixup operation is applied to augment new domains between labeled and unlabeled domains, which is beneficial for boosting the generalization capability of the model. Extensive results on publicly available DG benchmark datasets show the efficacy of our proposed SSDG method. Copyright © 2021, The Authors. All rights reserved.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Learning Hybrid Negative Probability Model for Weakly-Supervised Whole Slide Image Recognition

Learning Hybrid Negative Probability Model for Weakly-Superv...

引用

International Conference on Acoustics, Speech, and Signal Processing (IcasSP)

作者： Yining Qiu Yuxi Li Jiafu Wu Zhenye Gan Mingmin Chi Yabiao Wang Chengjie Wang Pei Wang School of Computer Science Shanghai Key Laboratory of Data Science Fudan University China Tencent Youtu Lab China Zhongshan PoolNet Technology Co. Ltd Zhongshan Fudan Joint Innovation Center China Zhejiang University China NAOC CAS China

Classifying an entire Whole Slide Image (WSI) in a single forward pass is challenging due to its vast resolution. Consequently, current effort on WSI classification resorts to multiple instance learning (MIL), using patch-wise instances to predict categories under image-wise supervision. However, recent MIL methods usually follow implicit instance selection strategy and ignore the effect from inherent patch category imbalances. In a statistical sense, negative patches dominate in WSIs and provide sufficient samples for accurate density estimation. Therefore, in this paper, we learn from anomaly detection and propose a deep MIL framework which learns a hybrid negative probability model to bootstrap discovery of potential positive lesion. We associate attention-based MIL approach with a regularization loss function to explicitly improve patch selection process in positive images. Experiments conducted on benchmarks of WSI recognition demonstrate that our method brings significant improvement to classic attention-based MIL baseline and achieves state-of-the-art performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

WiOpen: A Robust Wi-Fi-based Open-set Gesture Recognition Framework

arXiv

引用

arXiv 2024年

作者： Zhang, Xiang Huang, Jingyang Yan, Huan Zhao, Peng Zhuang, Guohang Liu, Zhi Liu, Bin CAS Key Laboratory of Electromagnetic Space Information University of Science and Technology of China Hefei230026 China School of Computer and Information Hefei University of Technology Hefei230601 China School of Big Data and Computer Science Guizhou Normal University Guiyang550025 China Department of Computer and Network Engineering The University of Electro-Communications Tokyo1828585 Japan

Recent years have witnessed a growing interest in Wi-Fi-based gesture recognition. However, existing works have predominantly focused on closed-set paradigms, where all testing gestures are predefined during training. This poses a significant challenge in real-world applications, as unseen gestures might be misclassified as known classes during testing. To address this issue, we propose WiOpen, a robust Wi-Fi-based Open-Set Gesture Recognition (OSGR) framework. Implementing OSGR requires addressing challenges caused by the unique uncertainty in Wi-Fi sensing. This uncertainty, resulting from noise and domains, leads to widely scattered and irregular data distributions in collected Wi-Fi sensing data. Consequently, data ambiguity between classes and challenges in defining appropriate decision boundaries to identify unknowns arise. To tackle these challenges, WiOpen adopts a two-fold approach to eliminate uncertainty and define precise decision boundaries. Initially, it addresses uncertainty induced by noise during data preprocessing by utilizing the CSI ratio. Next, it designs the OSGR network based on an uncertainty quantification method. Throughout the learning process, this network effectively mitigates uncertainty stemming from domains. Ultimately, the network leverages relationships among samples’ neighbors to dynamically define open-set decision boundaries, successfully realizing OSGR. Comprehensive experiments on publicly accessible datasets confirm WiOpen’s effectiveness. Notably, WiOpen also demonstrates superiority in cross-domain tasks when compared to state-of-the-art approaches. © 2024, CC BY-SA.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

A Dual-Channel Framework for Sarcasm Recognition by Detecting Sentiment Conflict

arXiv

引用

arXiv 2021年

作者： Liu, Yiyi Wang, Yequan Sun, Aixin Meng, Xuying Li, Jing Guo, Jiafeng CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Beijing Academy of Artificial Intelligence Beijing China School of Computer Science and Engineering Nanyang Technological University Singapore Singapore Institute of Computing Technology Chinese Academy of Sciences Beijing China Inception Institute of Artificial Intelligence Abu Dhabi United Arab Emirates

Sarcasm employs ambivalence, where one says something positive but actually means negative, and vice versa. The essence of sarcasm, which is also a sufficient and necessary condition, is the conflict between literal and implied sentiments expressed in one sentence. However, it is difficult to recognize such sentiment conflict because the sentiments are mixed or even implicit. As a result, the recognition of sophisticated and obscure sentiment brings in a great challenge to sarcasm detection. In this paper, we propose a Dual-Channel Framework by modeling both literal and implied sentiments separately. Based on this dual-channel framework, we design the Dual-Channel network (DC-Net) to recognize sentiment conflict. Experiments on political debates (i.e., IAC-V1 and IAC-V2) and Twitter datasets show that our proposed DC-Net achieves state-of-the-art performance on sarcasm recognition. Our code is released to support research https://***/yiyi-ict/dual-channel-for-sarcasm. © 2021, CC BY.

关键词：

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：