检索结果-内蒙古大学图书馆

12th International Conference on Image and Graphics, ICIG 2023

作者： Li, Xinjie Tang, Jianxiong Lai, Jianhuang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China

ISBN: (纸本)9783031463075

In recent years, spiking neural networks (SNNs) have gained significant attention due to bio-inspired working mechanism. The VGG-like and ResNet-like architectures are widely used for SNNs modeling. However, the spiking features of such architectures are generated by the layer-wise Integrate-and-Fire (IF) dynamics. The firing of deep neurons is independent of the neurons in the shallow layers. In this paper, we propose Multi-Compartment Spiking Neural Network (MC-SNN) that integrates the MPs of the shallow neurons to fire the deep neurons. Specifically, the MC-SNN is modeled by a Multi-Compartment Leaky Integrate-and-Fire (MC-LIF) neuron and an Adaptive Gating Unit (AGU). The MC-LIF neuron models the IF dynamics using the MPs from both deep and shallow layers, and the AGU adaptively scales the MPs of the MC-LIF neuron. These increase the information interaction between spiking neurons and improve the performance of SNNs. Besides, we design the Binarized Synaptic Encoder (BSE) to reduce the computation cost for the input of SNNs. Experimental results show that the MC-SNN performs well on the neuromorphic datasets, reaching 79.52% and 81.24% on CIFAR10-DVS and N-Caltech101, respectively. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Contour-guided person re-identification 2nd

Contour-guided person re-identification

引用

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

作者： Chen, Jiaxing Yang, Qize Meng, Jingke Zheng, Wei-Shi Lai, Jian-Huang School of Data and Computer Science Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Beijing China

ISBN: (纸本)9783030317256

Feature representation is one of the crucial components in person re-identificationre-ID. Recently, local feature has attracted great attention from the re-ID community, and extra visual cues have been well exploited to guide local feature learning, such as pose cues, semantic parsing and etc. Besides, the latest research demonstrates that general CNN-based deep models have a bias to texture feature in pattern recognition, but ignore shape-based feature, which has been verified as significant for cross-domain invariance. As far as we know, there is little work focusing on shape-based feature on person re-ID. In this paper, we introduce a new data modality, pedestrian contour, into the re-ID community, which to our best knowledge is the first attempt to utilize contour explicitly in deep re-ID models. We hypothesize that, as an alternative of other exploited visual cues, pedestrian contour could guide deep models to learn robust shape-based feature, with build-in prior information. We propose several contour-guided architectures to explicitly use pedestrian contour, including plain ones and multi-scale one. Extensive experiments have validated the effectiveness of our models. Moreover, we transfer the methodology into a powerful part-based model, Part-based Convolutional BaselinePCB, and boost the model performance, which verifies the promising prospect of contour-guided models to expand as an auxiliary mechanism in re-ID. © Springer Nature Switzerland AG 2019.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Gecnn-crf for prostate cancer detection with wsi

Gecnn-crf for prostate cancer detection with wsi

引用

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

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：