检索结果-内蒙古大学图书馆

Chinese Intelligent Systems Conference, CISC 2020

作者： Dong, Jinfeng Guo, Xuemei Wang, Guoli School of Data and Computer Science Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China

ISBN: (纸本)9789811584497

Pathological examination is of great significance for the diagnosis and treatment of prostate cancer, but artificial pathological examination is time-consuming, laborious and error prone. Automatic pathological examination can assist doctors in diagnosis and treatment. In this paper, a deep learning convolution network based on group equivariant convolution and conditional random field is proposed, which solves the problem of inconsistent features of data after random rotation in the learning process and enhances the robustness of the network. On the other hand, the conditional random field method is used to produce the same result on the slice image, which makes the segmentation edge of the probability image clearer. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Revealing Distribution Discrepancy by Sampling Transfer in Unlabeled Data 38

Revealing Distribution Discrepancy by Sampling Transfer in U...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhao, Zhilin Cao, Longbing Fan, Xuhui Zheng, Wei-Shi School of Computing Macquarie University Australia School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

There are increasing cases where the class labels of test samples are unavailable, creating a significant need and challenge in measuring the discrepancy between training and test distributions. This distribution discrepancy complicates the assessment of whether the hypothesis selected by an algorithm on training samples remains applicable to test samples. We present a novel approach called Importance Divergence (I-Div) to address the challenge of test label unavailability, enabling distribution discrepancy evaluation using only training samples. I-Div transfers the sampling patterns from the test distribution to the training distribution by estimating density and likelihood ratios. Specifically, the density ratio, informed by the selected hypothesis, is obtained by minimizing the Kullback-Leibler divergence between the actual and estimated input distributions. Simultaneously, the likelihood ratio is adjusted according to the density ratio by reducing the generalization error of the distribution discrepancy as transformed through the two ratios. Experimentally, I-Div accurately quantifies the distribution discrepancy, as evidenced by a wide range of complex data scenarios and tasks. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

94LVI Algorithms of OIpU(One-Iteration-per-Update) Type Handling Time-Dependent QP(Quadratic Programming) with Two Constraints 41

94LVI Algorithms of OIpU(One-Iteration-per-Update) Type Hand...

引用

第41届中国控制会议

作者： Yunong Zhang Zhiwen Yuan School of Computer Science and Engineering Sun Yat-sen University Guangdong Key Laboratory of Modern Control Technology Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Research Institute of Sun Yat-sen University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This paper presents three relatively effective numerical algorithms,i.e.,94 LVI algorithms of OIpU(one-iteration-perupdate) type,to handle time-dependent QP(quadratic programming) problems subject to two constraints respectively(i.e.,equality and inequality constraints,equality and bound constraints,or inequality and bound constraints).Specifically,two "bridges" play essential parts of the methods(i.e.,the first "bridge" makes a QP problem convert to an LVI [linear variational inequality],and the second "bridge" makes the LVI convert to a PLPE [piecewise-linear projection equation]).On the basis of the standard94 LVI algorithm,the methods only update once through the solution of the previous sampling time ***,we conduct a number of experiments to substantiate the three algorithms respectively,which use exponential functions,log functions,and trigonometric functions in corresponding coefficients of the experimental examples.

关键词： Quadratic programming Time-dependent Numerical algorithms Linear variational inequalities(LVI)

来源：评论

学校读者我要写书评

暂无评论

ALGCN: Accelerated Light Graph Convolution Network for Recommendation 28th

ALGCN: Accelerated Light Graph Convolution Network for Reco...

引用

28th International Conference on Database Systems for advanced Applications, DASFAA 2023

作者： Xu, Ronghai Zhao, Haijun Li, Zhi-Yuan Wang, Chang-Dong School of Computer Science and Engineering Sun Yat-sen University Guangdong Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Beijing China

ISBN: (纸本)9783031306716

Recently, Graph Convolutional Network (GCN) has been widely applied in the field of collaborative filtering (CF) with tremendous success, since its message-passing mechanism can efficiently aggregate neighborhood information between users and items. However, most of the existing GCN-based CF models suffer from low convergence rates during training, mainly because they follow the design of standard GCN using a simple uniform average to aggregate the neighborhood information. We also find that the scale of embedding across different layers oscillates. We argue that these issues can be alleviated by our proposed graph convolution framework, namely Accelerated Light Graph Convolutional Network (ALGCN). ALGCN mainly contains two components: influence-aware graph convolution operation and augmentation-free in-batch contrastive loss on the unit sphere. Empirical evaluations on three large and public datasets demonstrate that the proposed method achieves remarkable training speedups over LightGCN and substantially outperforms the state-of-the-art GCN-based CF models. Our method also shows a great improvement in long-tail recommendation. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

ProtoMix: Learnable Data Augmentation on Few-Shot Features with Vector Quantization in CTR Prediction 9th

ProtoMix: Learnable Data Augmentation on Few-Shot Features ...

引用

19th International Conference on advanced Data Mining and Applications, ADMA 2023

作者： Zhao, Haijun Xu, Ronghai Wang, Chang-Dong Jiang, Ying School of Computer Science and Engineering Sun Yat-sen University Guangdong Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China

ISBN: (纸本)9783031466601

Click-Through Rate (CTR) prediction is a critical problem in recommendation systems since it involves enormous business interest. Most deep CTR model follows an Embedding & Feature Interaction paradigm. However, the feature interaction module cannot work well without a good embedding representation of features. Due to the long-tail phenomenon in real scenes, few samples are provided in the dataset for a large proportion of features. In this paper, we present ProtoMix, a model-agnostic framework for learnable data augmentation on few-shot features in CTR prediction. ProtoMix automatically extracts information from co-occurred features within the same instance to assign prototype embedding with vector quantization for few-shot features and further synthesize the embedding representation of the augmented virtual instance for training. Original embedding, feature interaction module, and the embedding generator are jointly trained on a well-designed objective in an end-to-end manner in ProtoMix. We experimentally validate the effectiveness and compatibility of ProtoMix by comparing it with baseline and other data augmentation methods on different deep CTR models and multiple real-world CTR benchmark datasets. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Stage-by-stage based design paradigm of two-pathway model for gaze following 1

引用

2nd Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2019

作者： Cao, Zhongping Wang, Guoli Guo, Xuemei School of Data and Computer Science Sun Yat-sen University Guangzhou510006 China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Beijing China

ISBN: (数字)9783030317232

ISBN: (纸本)9783030317225

Gaze, which is an important non-verbal cue of interactions between human beings, can be used to estimate a person’s point of regard as well as deduce his intention. And gaze following is an task to estimate the visual attention of people in a single image. To tackle this challenging problem, earlier state-of-the-art work try to combine the information from image saliency as well as the gaze directions of people, thus demonstrate a deep-learning based two-pathway model. However, previous work do not focus much on why such a two-pathway model works well. Thus, in this paper, we divide the two-pathway model into three stages, compare different mechanisms in those stages to better understand how each stage may influence the model performance. Finally, we find out the best combinations of the mechanism in three stages and evaluate the model on the benchmark GazeFollow. © Springer Nature Switzerland AG 2019.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Solving Multitrip Pickup and Delivery Problem With Time Windows and Manpower Planning Using Multiobjective Algorithms

引用

IEEE/CAA Journal of Automatica Sinica 2020年第4期7卷 1134-1153页

作者： Jiahai Wang Yuyan Sun Zizhen Zhang Shangce Gao the Department of Computer Science and also with the Key Laboratory of Machine Intelligence and Advanced ComputingMinistry of Educationand also with the Guangdong Key Laboratory of Big Data Analysis and ProcessingSun Yat-sen UniversityGuangzhou 510275China the Department of Computer Science Sun Yat-sen UniversityGuangzhou 510275China the Faculty of Engineering University of ToyamaToyama-shi 930-8555Japan

The multitrip pickup and delivery problem with time windows and manpower planning(MTPDPTW-MP)determines a set of ambulance routes and finds staff assignment for a hospital. It involves different stakeholders with diverse interests and objectives. This study firstly introduces a multiobjective MTPDPTW-MP(MO-MTPDPTWMP) with three objectives to better describe the real-world scenario. A multiobjective iterated local search algorithm with adaptive neighborhood selection(MOILS-ANS) is proposed to solve the problem. MOILS-ANS can generate a diverse set of alternative solutions for decision makers to meet their requirements. To better explore the search space, problem-specific neighborhood structures and an adaptive neighborhood selection strategy are carefully designed in MOILS-ANS. Experimental results show that the proposed MOILS-ANS significantly outperforms the other two multiobjective algorithms. Besides, the nature of objective functions and the properties of the problem are analyzed. Finally, the proposed MOILS-ANS is compared with the previous single-objective algorithm and the benefits of multiobjective optimization are discussed.

关键词： Adaptive neighborhood selection manpower planning multiobjective optimization multitrip pickup and delivery problem with time windows

来源：评论

学校读者我要写书评

暂无评论

Halftone Image Steganography with Distortion Measurement Based on Structural Similarity 18th

Halftone Image Steganography with Distortion Measurement Bas...

引用

18th International Workshop on Digital Forensics and Watermarking, IWDW 2019

作者： Liu, Wanteng Yin, Xiaolin Lu, Wei Zhang, Junhong School of Data and Computer Science Guangdong Key Laboratory of Information Security Technology Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing Sun Yat-sen University Guangzhou510006 China

ISBN: (纸本)9783030435745

For halftone image data hiding, it is difficult to achieve good visual quality and statistical security when high embedding capacity is demanded. In this paper, a secure steganographic scheme for halftone image is proposed, which aims to minimize the embedding distortion on structural similarity. Structural distortions are the ones that affect the most the perception of degradation of a halftone image. To evaluate the structural distortions caused by flipping pixels, halftone image structural similarity (HSSIM) is introduced based on a human visual filter, which is trained by Least-Mean-Square (LMS) approach. Utilizing the HSSIM, a distortion measurement is proposed to evaluate the embedding distortions on both vision and statistics. To minimize the embedding distortions, syndrome-trellis code (STC) is employed in the embedding process. The experimental results have demonstrated that the proposed steganographic scheme can achieve high statistical security with good visual quality without degrading the embedding capacity. © 2020, Springer Nature Switzerland AG.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

VISUALLY MAINTAINED IMAGE DISTURBANCE AGAINST DEEPFAKE FACE SWAPPING

VISUALLY MAINTAINED IMAGE DISTURBANCE AGAINST DEEPFAKE FACE ...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Dong, Junhao Xie, Xiaohua School of Computer Science and Engineering Sun Yat-sen University China Guangdong Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (纸本)9781665438643

As a deep learning-based application, DeepFake can generate malicious images or videos through replacing the face of a source image with the target face, which poses a significant threat to social media. In this paper, we propose a scheme to prevent such tampering by exploring adversarial examples against DeepFake. Specifically, adversarial examples are produced by adding tailored distortion to source images. The added distortion is imperceptible to human vision but can mislead the generation of face-swapped images effectively. We present three novel adversarial attacks against DeepFake autoencoders from perspectives of adversarial transferability and latent representation. Our first method synthesizes universal perturbation, which is image-agnostic. By contrast, the latter two methods directly perform the preciser perturbation specific to a source image. Extensive experiments demonstrate the effectiveness of our adversarial examples against DeepFake in terms of both reference and non-reference image quality assessment. © 2021 IEEE

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Euler-Discretized GZ-Type Complex Neuronet computing Real-Time Varying Complex Matrix Inverse 36

Euler-Discretized GZ-Type Complex Neuronet Computing Real-Ti...

引用

第36届中国控制会议

作者： Yunong Zhang Guofu Wu Binbin Qiu Wan Li Penghao He School of Information Science and Technology Sun Yat-sen University(SYSU) Key Laboratory of Autonomous Systems and Networked Control Ministry of Education SYSU-CMU Shunde International Joint Reseach Institute Key Laboratory of Machine Intelligence and Advanced Computing(Sun Yat-sen University) Ministry of Education

ISBN: (纸本)9781538629185

In this paper,a GZ-type complex neuronet（generated by combining gradient dynamic system and Zhang dynamic system） is illustrated and discretized into an Euler-discretized（i.e.,discretized by Euler forward rule） GZ-type complex neuronet for computing real-time varying complex matrix *** results not only show the efficacy of the proposed Eulerdiscretized GZ-type neuronet but also verify that the error pattern is square.

关键词： GZ-Type Neuronet Complex Matrix Inverse Euler Forward Rule Computer Simulation Error Pattern

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：