检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Xu, Fangzhi Liu, Jun Lin, Qika Zhao, Tianzhe Zhang, Jian Zhang, Lingling School of Computer Science and Technology Xi’an Jiaotong University Xi’an China Shaanxi Province Key Laboratory of Satellite and Terrestrial Network Tech. R&D National Engineering lab for Big Data Analytics Xi’an China

Logical reasoning task involves diverse types of complex reasoning over text, based on the form of multiple-choice question answering. Given the context, question and a set of options as the input, previous methods achieve superior performances on the full-data setting. However, the current benchmark dataset has the ideal assumption that the reasoning type distribution on the train split is close to the test split, which is inconsistent with many real application scenarios. To address it, there remain two problems to be studied: (1) How is the zero-shot capability of the models (train on seen types and test on unseen types)? (2) How to enhance the perception of reasoning types for the models? For problem 1, we propose a new benchmark for generalized zero-shot logical reasoning, named ZsLR. It includes six splits based on the three type sampling strategies. For problem 2, a type-aware model TaCo is proposed. It utilizes both the heuristic input reconstruction and the contrastive learning to improve the type perception in the global representation. Extensive experiments on both the zero-shot and full-data settings prove the superiority of TaCo over the state-of-the-art methods. Also, we experiment and verify the generalization capability of TaCo on other logical reasoning dataset. © 2023, CC BY.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Backdoor Defense via Deconfounded Representation Learning

arXiv

引用

arXiv 2023年

作者： Zhang, Zaixi Liu, Qi Wang, Zhicai Lu, Zepu Hu, Qingyong Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence Anhui Hefei China Hong Kong University of Science and Technology Hong Kong University of Science and Technology of China China

Deep neural networks (DNNs) are recently shown to be vulnerable to backdoor attacks, where attackers embed hidden backdoors in the DNN model by injecting a few poisoned examples into the training dataset. While extensive efforts have been made to detect and remove backdoors from backdoored DNNs, it is still not clear whether a backdoor-free clean model can be directly obtained from poisoned datasets. In this paper, we first construct a causal graph to model the generation process of poisoned data and find that the backdoor attack acts as the confounder, which brings spurious associations between the input images and target labels, making the model predictions less reliable. Inspired by the causal understanding, we propose the Causality-inspired Backdoor Defense (CBD), to learn deconfounded representations for reliable classification. Specifically, a backdoored model is intentionally trained to capture the confounding effects. The other clean model dedicates to capturing the desired causal effects by minimizing the mutual information with the confounding representations from the backdoored model and employing a sample-wise re-weighting scheme. Extensive experiments on multiple benchmark datasets against 6 state-of-the-art attacks verify that our proposed defense method is effective in reducing backdoor threats while maintaining high accuracy in predicting benign samples. Further analysis shows that CBD can also resist potential adaptive attacks. The code is available at https://***/zaixizhang/CBD. © 2023, CC BY-NC-SA.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

TOWARDS EFFECTIVE ADVERSARIAL ATTACK AGAINST 3D POINT CLOUD CLASSIFICATION

TOWARDS EFFECTIVE ADVERSARIAL ATTACK AGAINST 3D POINT CLOUD ...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Ma, Chengcheng Meng, Weiliang Wu, Baoyuan Xu, Shibiao Zhang, Xiaopeng NLPR Institute of Automation Chinese Academy of Sciences China Zhejiang Lab China The State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China School of Data Science The Chinese University of Hong Kong Shenzhen China Shenzhen Research Institute of Big Data China

ISBN: (纸本)9781665438643

In the domain of 3D point cloud classification, deep learning based classifiers have made significant progress, while they have been also proven to be vulnerable on the adversarial attack at the same time. Some recent works employ the attack methods that devised for image classification such as projected gradient descent (PGD) to attack the 3D classifiers, but their performances seem quite limited when faced with statistical operations including point cloud denoising and point cloud upsampling. In this paper, we propose 'SmoothAttack', a new attack that can craft adversarial point clouds robust to statistical operations. SmoothAttack can be easily applied in both global constraint and pointwise constraint. Besides, we analyze the directions of perturbations onto the point cloud during the iteration process, where SmoothAttack can somehow stabilize the direction and make full use of the adversarial budgets. Experiments validate that our 'SmoothAttack' can raise the attack success rates against statistical defenses up to 98% for untargeted attack and 91% for targeted attack on ModelNet40 database when fooling the classifiers PointNet and DGCNN. © 2021 IEEE

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Fast and Scalable Gate-Level Simulation in Massively Parallel Systems

Fast and Scalable Gate-Level Simulation in Massively Paralle...

引用

IEEE International Conference on Computer-Aided Design

作者： Haichuan Hu Zichen Xu Yuhao Wang Fangming Liu Services Computing Technology and System Lab Cluster and Grid Computing Lab National Engineering Research Center for Big Data Technology and System School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Mathematics and Computer Science Nanchang University Nanchang China Pengcheng Laboratory Shenzhen China

The natural bijection between a proposed circuit design and its graph representation shall allow any graph optimization algorithm deploying into many-core systems efficiently. However, this process suffers from the exponentially growing overhead and heavy memory footprint with the signal propagation. To conquer the unique challenge, we systematically study the simulation with millions of gates, and identify that the processing complexity could grow exponentially from the signal inputs, the skewness of the computational graph stays. Thus, we present ZhouBi, a fast and scalable gate-level simulation framework to fully exploit the parallelism from many-core systems. ZhouBi contributes in threefolds, (I) a graph representation that colors gate-level netlists and identifies skew partitions based on the graph skewness; (II) A set of heuristic algorithms that picks opportunistic and conservative algorithms to accelerate the simulation; (III) A system facility that supports selective mapping between simulation and many-core, providing a tradeoff between the risk of concurrent simulation fail and performance gain. We have prototyped ZhouBi and evaluated it with practical baselines. ZhouBi can achieve a 27.6× performance gain, as compared to the state-of-the-practice Veriwell without compromising any correctness. Our framework supports large graphs enabling scale-out gate-level simulations for chip design.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intelligent pneumonia image recognition and classification method based on improved convolutional neural network 4

Intelligent pneumonia image recognition and classification m...

引用

4th IEEE International Conference on Automation, Electronics and Electrical Engineering, AUTEEE 2021

作者： Liu, Jiahang Zhao, Wenkang Li, Zongyi Song, Zeyang Toe, Teoh Teik Artificial Intelligence of Automation University of Science and Techonology Beijing Beijing China Data Science and Big Data Technology Harbin Institute of Technology Harbin China Beijing University of Posts and Telecommunications Telecommunications Engineering With Management Beijing China Nanjing Tech University Mechanical Engineering Nanjing China Nanyang Technological University NTU Business AI Lab Singapore Singapore

ISBN: (纸本)9781665428392

This paper is an attempt to apply neural networks to classify pneumonia images. The classifying model is built based on thousands of the actual X-ray images, which relatively belong to both pneumonia patients and normal people. The classification neural network, a popular way of machine learning, will serve as a supplementary means to help diagnose pneumonia and perform pre-screening. The paper analyzes and contains details of the algorithms we used. By analyzing the structure of the network, we come up with several useful methods to improve the model, so as to achieve a better model structure and application to classification. The new structure we propose is demonstrated in this paper. The final training accuracy is over 95% and the test accuracy is approximately 92%. © 2021 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detection

arXiv

引用

arXiv 2022年

作者： Liang, Siyuan Wu, Baoyuan Fan, Yanbo Wei, Xingxing Cao, Xiaochun Institute of Information Engineering Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China School of Data Science The Chinese University of Hong Kong Shenzhen China Secure Computing Lab of Big Data Shenzhen Research Institute of Big Data Shenzhen China Tencent Shenzhen China Institute of Artificial Intelligence Hangzhou Innovation Institute Beihang University Beijing China

Object detection has been widely used in many safety-critical tasks, such as autonomous driving. However, its vulnerability to adversarial examples has not been sufficiently studied, especially under the practical scenario of black-box attacks, where the attacker can only access the query feedback of predicted bounding-boxes and top-1 scores returned by the attacked model. Compared with black-box attack to image classification, there are two main challenges in black-box attack to detection. Firstly, even if one bounding-box is successfully attacked, another suboptimal bounding-box may be detected near the attacked bounding-box. Secondly, there are multiple bounding-boxes, leading to very high attack cost. To address these challenges, we propose a Parallel Rectangle Flip Attack (PRFA) via random search. We explain the difference between our method with other attacks in Fig. 1. Specifically, we generate perturbations in each rectangle patch to avoid sub-optimal detection near the attacked region. Besides, utilizing the observation that adversarial perturbations mainly locate around objects' contours and critical points under white-box attacks, the search space of attacked rectangles is reduced to improve the attack efficiency. Moreover, we develop a parallel mechanism of attacking multiple rectangles simultaneously to further accelerate the attack process. Extensive experiments demonstrate that our method can effectively and efficiently attack various popular object detectors, including anchor-based and anchor-free, and generate transferable adversarial examples. Copyright © 2022, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Where is My Spot? Few-shot Image Generation via Latent Subspace Optimization

Where is My Spot? Few-shot Image Generation via Latent Subsp...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Chenxi Zheng Bangzhen Liu Huaidong Zhang Xuemiao Xu Shengfeng He South China University of Technology State Key Laboratory of Subtropical Building Science Ministry of Education Key Laboratory of Big Data and Intelligent Robot Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information Singapore Management University

Image generation relies on massive training data that can hardly produce diverse images of an unseen category according to a few examples. In this paper, we address this dilemma by projecting sparse few-shot samples into a continuous latent space that can potentially generate infinite unseen samples. The rationale behind is that we aim to locate a centroid latent position in a conditional StyleGAN, where the corresponding output image on that centroid can maximize the similarity with the given samples. Although the given samples are unseen for the conditional StyleGAN, we assume the neighboring latent subspace around the centroid belongs to the novel category, and therefore introduce two latent subspace optimization objectives. In the first one we use few-shot samples as positive anchors of the novel class, and adjust the StyleGAN to produce the corresponding results with the new class label condition. The second objective is to govern the generation process from the other way around, by altering the centroid and its surrounding latent subspace for a more precise generation of the novel class. These reciprocal optimization objectives inject a novel class into the StyleGAN latent subspace, and therefore new unseen samples can be easily produced by sampling images from it. Extensive experiments demonstrate superior few-shot generation performances compared with state-of-the-art methods, especially in terms of diversity and generation quality. Code is available at https://***/chansey0529/LSO.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PSMiner: A Pattern-Aware Accelerator for High-Performance Streaming Graph Pattern Mining

PSMiner: A Pattern-Aware Accelerator for High-Performance St...

引用

Design Automation Conference

作者： Hao Qi Yu Zhang Ligang He Kang Luo Jun Huang Haoyu Lu Jin Zhao Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Zhejiang Lab Zhejiang-HUST Joint Research Center for Graph Processing China Department of Computer Science University of Warwick United Kingdom

Streaming Graph Pattern Mining (GPM) has been widely used in many application fields. However, the existing streaming GPM solution suffers from many unnecessary explorations and isomorphism tests, while the existing static GPM ones require many repetitive operations to compute the full graph. In this paper, we propose a pattern-aware incremental execution approach and design the first streaming GPM accelerator called PSMiner, which integrates multiple optimizations to reduce redundant computation and improve computing efficiency. We have conducted extensive experiments. The results show that compared with the state-of-the-art software and hardware solutions, PSMiner achieves the average speedups of 770.9× and 60.4×, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Classification of Intrahepatic Cholangiocarcinoma and Hepatocellular Carcinoma with Four-Phase Ct Images

SSRN

引用

SSRN 2024年

作者： Zhu, Wentao Wu, Yuanfeng Feng, Zhan Cui, Heng Rao, Fan Ni, Yangfan Chen, Geng Xia, Yong Zhejiang Lab Hangzhou China Department of Radiology College of Medicine The First Affiliated Hospital Zhejiang University China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an China

Liver cancer is one of the leading causes of cancer-related death globally. The differentiation of hepatic tumors is critical for designing an accurate treatment plan and improving the five-year survival rate. Recently, multiphase CT images have become the first-line examination approach for clinical diagnosis. Existing methods have been proposed to distinguish hepatic tumors based on deep learning using multiphase CT. However, CNN-based models fail to explicitly establish temporal relationships among different phases, and RNN-based methods rely on expensive calculations due to the recurrent mechanism. In this paper, we proposed a transformer-based deep learning method for identifying intrahepatic cholangiocarcinoma and hepatocellular carcinoma using four-phase CT images as input. Specifically, a difference attention module was developed to improve the feature representation by using the phase difference as interphase temporal information. Moreover, a transformer-based structure was used for classification to explore the long-term context and capture the temporal relationship among phases using a multihead self-attention module. Experiments with clinical datasets are implemented to evaluate the performance of the proposed method and mainstream methods. In the experiments, the proposed method demonstrated superior performance in classifying ICC and HCC on the test set, with an accuracy of 83.72%, a sensitivity of 0.7511, a specificity of 0.9200 and an AUC of 0.90. The results indicate that the proposed method outperforms the traditional deep learning based methods. The architecture can be utilized in other researches using multiple images as input. © 2024, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Expediting Distributed GNN Training with Feature-only Partition and Optimized Communication Planning

Expediting Distributed GNN Training with Feature-only Partit...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE Computer and Communications Societies

作者： Bingqian Du Jun Liu Ziyue Luo Chuan Wu Qiankun Zhang Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Department of Electrical and Computer Engineering The Ohio State University USA Department of Computer Science The University of Hong Kong Hong Kong School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9798350383508

ISBN: (纸本)9798350383515

Feature-only partition of large graph data in distributed Graph Neural Network (GNN) training offers advantages over commonly adopted graph structure partition, such as minimal graph preprocessing cost and elimination of cross-worker subgraph sampling burdens. Nonetheless, performance bottleneck of GNN training with feature-only partitions still largely lies in the substantial communication overhead due to cross-worker feature fetching. To reduce the communication overhead and expedite distributed training, we first investigate and answer two key questions on convergence behaviors of GNN model in feature-partition based distribute GNN training: 1) As no worker holds a complete copy of each feature, can gradient exchange among workers compensate for the information loss due to incomplete local features? 2) If the answer to the first question is negative, is feature fetching in every training iteration of the GNN model necessary to ensure model convergence? Based on our theoretical findings on these questions, we derive an optimal communication plan that decides the frequency for feature fetching during the training process, taking into account bandwidth levels among workers and striking a balance between model loss and training time. Extensive evaluation demonstrates consistent results with our theoretical analysis, and the effectiveness of our proposed design.

关键词： Training Time-frequency analysis Costs Computational modeling Distributed databases Bandwidth Graph neural networks

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：