检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhong, Xiaojing Huang, Xinyi Wu, Zhonghua Lin, Guosheng Wu, Qingyao School of Software Engineering South China University of Technology China School of Computer Science and Engineering Nanyang Technological University Singapore Key Laboratory of Big Data and Intelligent Robot Ministry of Education China Peng Cheng Laboratory China SenseTime Research China

Makeup transfer is a process of transferring the makeup style from a reference image to the source image, while preserving the source image’s identity. In addition to achieving fine-grained control over the makeup transfer, incorporating semantic alignment into the transformation is crucial, as the poses of the reference and source images are often inconsistent. We propose a novel Semantic-guided Alignment and Region-Adaptive normalization framework (SARA) to effectively transfer makeup styles under misaligned poses, offering flexible control to meet the demands of real-world applications, such as partial transfer, intensity adjustment, and makeup removal. Specifically, SARA comprises three modules: Firstly, we propose a semantic-guided alignment module to explicitly construct dense correspondence between the reference image and the target semantic map, employing unbalanced optimal transport matching to handle semantic region mismatches. Secondly, a region-adaptive normalization module is responsible for dynamically combining the warped style features with shape-independent style codes obtained by region-wise average pooling, mitigating feature loss during the alignment. Lastly, a makeup fusion module progressively fuses the identity features with the makeup styles to render the final output image. Furthermore, we combine optimal transport with histogram matching to generate the pseudo ground truth, which is used to facilitate the transfer in terms of both spatial alignment and color distribution. Experimental results show that our proposed SARA outperforms existing methods on two public datasets. © 2023, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Semantic-Constraint Matching Transformer for Weakly Supervised Object Localization

arXiv

引用

arXiv 2023年

作者： Cao, Yiwen Su, Yukun Wang, Wenjun Liu, Yanxia Wu, Qingyao The School of Software Engineering South China University of Technology Guangzhou510640 China The Key Laboratory of Big Data and Intelligent Robot Ministry of Education Guangzhou China The School of Computer Science and Engineering Nanyang Technological University Singapore The Pazhou Lab Guangzhou China

Weakly supervised object localization (WSOL) strives to learn to localize objects with only image-level supervision. Due to the local receptive fields generated by convolution operations, previous CNN-based methods suffer from partial activation issues, concentrating on the object's discriminative part instead of the entire entity scope. Benefiting from the capability of the self-attention mechanism to acquire long-range feature dependencies, Vision Transformer has been recently applied to alleviate the local activation drawbacks. However, since the transformer lacks the inductive localization bias that are inherent in CNNs, it may cause a divergent activation problem resulting in an uncertain distinction between foreground and background. In this work, we proposed a novel Semantic-Constraint Matching Network (SCMN) via transformer to converge on the divergent activation. Specifically, we first propose a local patch shuffle strategy to construct the image pairs, disrupting local patches while guaranteeing global consistency. The paired images that contain the common object in spatial are then fed into the Siamese network encoder. We further design a semantic-constraint matching module, which aims to mine the co-object part by matching the coarse class activation maps (CAMs) extracted from the pair images, thus implicitly guiding and calibrating the transformer network to alleviate the divergent activation. Extensive experimental results conducted on two challenging benchmarks including CUB-200-2011 and ILSVRC datasets show that our method can achieve the new state-of-the-art performance and outperform the previous method by a large margin. Copyright © 2023, The Authors. All rights reserved.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

Learning Cooperative Beamforming with Edge-Update Empowered Graph Neural Networks

arXiv

引用

arXiv 2022年

作者： Wang, Yunqi Li, Yang Shi, Qingjiang Wu, Yik-Chung Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Shenzhen Research Institute of Big Data Shenzhen China School of Software Engineering Tongji University Shanghai China

Cooperative beamforming design has been recognized as an effective approach in modern wireless networks to meet the dramatically increasing demand of various wireless data traffics. It is formulated as an optimization problem in conventional approaches and solved iteratively in an instance-by-instance manner. Recently, learning-based methods have emerged with real-time implementation by approximating the mapping function from the problem instances to the corresponding solutions. Among various neural network architectures, graph neural networks (GNNs) can effectively utilize the graph topology in wireless networks to achieve better generalization ability on unseen problem sizes. However, the current GNNs are only equipped with the node-update mechanism, which restricts it from modeling more complicated problems such as the cooperative beamforming design, where the beamformers are on the graph edges of wireless networks. To fill this gap, we propose an edge-graph-neural-network (Edge-GNN) by incorporating an edge-update mechanism into the GNN, which learns the cooperative beamforming on the graph edges. Simulation results show that the proposed Edge-GNN achieves higher sum rate with much shorter computation time than state-of-the-art approaches, and generalizes well to different numbers of base stations and user equipments. Copyright © 2022, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learning 24

Towards High-resolution 3D Anomaly Detection via Group-Level...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Zhu, Hongze Xie, Guoyang Hou, Chengbin Dai, Tao Gao, Can Wang, Jinbao Shen, Linlin National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Computer Science City University of Hong Kong Hong Kong Hong Kong Department of Intelligent Manufacturing CATL Ningde China Fuzhou Fuyao Institute for Advanced Study Fuyao University of Science and Technology Fuzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

ISBN: (纸本)9798400706868

High-resolution point clouds (HRPCD) anomaly detection (AD) plays a critical role in precision machining and high-end equipment manufacturing. Despite considerable 3D-AD methods that have been proposed recently, they still cannot meet the requirements of the HRPCD-AD task. There are several challenges: i) It is difficult to directly capture HRPCD information due to large amounts of points at the sample level;ii) The advanced transformer-based methods usually obtain anisotropic features, leading to degradation of the representation;iii) The proportion of abnormal areas is very small, which makes it difficult to characterize. To address these challenges, we propose a novel group-level feature-based network, called Group3AD, which has a significantly efficient representation ability. First, we design an Intercluster Uniformity Network (IUN) to present the mapping of different groups in the feature space as several clusters, and obtain a more uniform distribution between clusters representing different parts of the point clouds in the feature space. Then, an Intracluster Alignment Network (IAN) is designed to encourage groups within the cluster to be distributed tightly in the feature space. In addition, we propose an Adaptive Group-Center Selection (AGCS) based on geometric information to improve the pixel density of potential anomalous regions during inference. The experimental results verify the effectiveness of our proposed Group3AD, which surpasses Reg3D-AD by the margin of 5% in terms of object-level AUROC on Real3D-AD. We provide the code and supplementary information on our website: https://***/M-3LAB/Group3AD. © 2024 ACM.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Rethinking the Bias of Foundation Model under Long-tailed Distribution

arXiv

引用

arXiv 2025年

作者： Chen, Jiahao Qin, Bin Li, Jiangmeng Chen, Hao Su, Bing Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods China Institute of Software Chinese Academy of Sciences China University of Chinese Academy of Sciences China Electrical and Computer Engineering Carnegie Mellon University United States

Long-tailed learning has garnered increasing attention due to its practical significance. Among the various approaches, the fine-tuning paradigm has gained considerable interest with the advent of foundation models. However, most existing methods primarily focus on leveraging knowledge from these models, overlooking the inherent biases introduced by the imbalanced training data they rely on. In this paper, we examine how such imbalances from pre-training affect long-tailed downstream tasks. Specifically, we find the imbalance biases inherited in foundation models on downstream task as parameter imbalance and data imbalance. During fine-tuning, we observe that parameter imbalance plays a more critical role, while data imbalance can be mitigated using existing re-balancing strategies. Moreover, we find that parameter imbalance cannot be effectively addressed by current re-balancing techniques, such as adjusting the logits, during training, unlike data imbalance. To tackle both imbalances simultaneously, we build our method on causal learning and view the incomplete semantic factor as the confounder, which brings spurious correlations between input samples and labels. To resolve the negative effects of this, we propose a novel backdoor adjustment method that learns the true causal effect between input samples and labels, rather than merely fitting the correlations in the data. Notably, we achieve an average performance increase of about 1.67% on each dataset. Copyright © 2025, The Authors. All rights reserved.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Keeping Pace with Ever-Increasing data: Towards Continual Learning of Code Intelligence Models

Keeping Pace with Ever-Increasing Data: Towards Continual Le...

引用

International Conference on software engineering (ICSE)

作者： Shuzheng Gao Hongyu Zhang Cuiyun Gao Chaozheng Wang School of Computer Science and Technology Harbin Institute of Technology Shenzhen China Peng Cheng Laboratory and Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies School of Big Data and Software Engineering Chongqing University China

Previous research on code intelligence usually trains a deep learning model on a fixed dataset in an offline manner. However, in real-world scenarios, new code repositories emerge incessantly, and the carried new knowledge is beneficial for providing up-to-date code intelligence services to developers. In this paper, we aim at the following problem: How to enable code intelligence models to continually learn from ever-increasing data? One major challenge here is catastrophic forgetting, meaning that the model can easily forget knowledge learned from previous datasets when learning from the new dataset. To tackle this challenge, we propose REPEAT, a novel method for continual learning of code intelligence models. Specifically, REPEAT addresses the catastrophic forgetting problem with representative exemplars replay and adaptive parameter regularization. The representative exemplars replay component selects informative and diverse exemplars in each dataset and uses them to re-train model periodically. The adaptive parameter regularization component recognizes important parameters in the model and adaptively penalizes their changes to preserve the knowledge learned before. We evaluate the proposed approach on three code intelligence tasks including code summarization, software vulnerability detection, and code clone detection. Extensive experiments demonstrate that REPEAT consistently outperforms baseline methods on all tasks. For example, REPEAT improves the conventional fine-tuning method by 1.22, 5.61, and 1.72 on code summarization, vulnerability detection and clone detection, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Container lifecycle-aware scheduling for serverless computing

Container lifecycle-aware scheduling for serverless computin...

引用

作者： Wu, Song Tao, Zhiheng Fan, Hao Huang, Zhuo Zhang, Xinmin Jin, Hai Yu, Chen Cao, Chun 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 State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing China

Elastic scaling in response to changes on demand is a main benefit of serverless computing. When bursty workloads arrive, a serverless platform launches many new containers and initializes function environments (known as cold starts), which incurs significant startup latency. To reduce cold starts, platforms usually pause a container after it serves a request, and reuse this container for subsequent requests. However, this reuse strategy cannot efficiently reduce cold starts because the schedulers are agnostic of container lifecycle. For example, it may ignore soon available containers or evict soon needed containers. We propose a container lifecycle-aware scheduling strategy for serverless computing, CAS. The key idea is to control distribution of requests and determine creation or eviction of containers according to different lifecycle phases of containers. We implement a prototype of CAS on OpenWhisk. Our evaluation shows that CAS reduces 81% cold starts and therefore brings a 63% reduction at 95th percentile latency compared with native scheduling strategy in OpenWhisk when there is worker contention between workloads, and does not add significant performance overhead. © 2021 John Wiley & Sons Ltd.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Graph-Augmented Contrastive Clustering for Time Series

SSRN

引用

SSRN 2023年

作者： Zhang, Qin Liang, Zhuoluo Ngueilbaye, Alladoumbaye Zhang, Peng Chen, Junyang Chen, Xiaojun Huang, Joshua Zhexue College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou510006 China

The recent emergence of time series contrastive clustering methods can be categorized into two classes. The first class uses contrastive learning for universal representations, which can be effective in various downstream tasks, but overlooks important categorical information and clustering objectives, leading to unsuitable models. The second class incorporates contrastive learning into clustering objectives, but fails to fully explore potential connections and structures between time series data. To this end, we propose the "Time Series Graph-augmented Contrastive Clustering (TSGCC) method", a graph-augmented contrastive learning framework aiming to create cluster-friendly features and assignments by iteratively optimizing contrastive loss. The method uses a weighted KNN graph to build positive and negative sample pairs, projecting the instances into a feature space with the dimensionality number of clusters. Experimental results demonstrate that TSGCC outperforms 18 advanced time-series clustering methods on the 36 representatives out of the 128 UCR benchmarks, achieving the best clustering results on 12 datasets, with the highest average rank (3.22) of RI and the second-highest average rank (3.89) of NMI among 18 clustering methods. We further compared our method with recent approaches on the entire set of 128 UCR datasets, demonstrating our method's broad applicability and effectiveness. © 2023, The Authors. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

3D Virtual Sand Table Display System of Industrial Park Based on Augmented Reality

3D Virtual Sand Table Display System of Industrial Park Base...

引用

2021 IEEE International Conference on Industrial Application of Artificial Intelligence, IAAI 2021

作者： Lu, Hongyan He, Jie Cen, Caichun He, Jie Wuzhou University School of Big Data and Software Engineering Wuzhou China Wuzhou University School of Electronic and Information Engineering Wuzhou China Key Laboratory of Image Processing and Intelligent Information System at Guangxi University Wuzhou University Wuzhou China

ISBN: (纸本)9781665495066

To improve the interactivity of 3D virtual sand table displays, an industrial park 3D virtual sand table display system based on augmented reality is designed. The system consists of multiple modules. The design of the animation browsing module is based on the roaming walking model environment. The walking and roaming module can enable participants to experience the real visual and tactile virtual space in the process of input browsing. In the surrounding environment and traffic condition module, the surrounding environment and traffic condition display are created by means of static pictures and picture buttons. The VRML scene space module is responsible for creating objects such as VRML viewpoints. Scenario module transformation completes event transmission through routing. The virtual sand table VRML optimization modeling module is responsible for constructing the virtual sand table VRML model. The function of the multiperson collaboration module is to provide collaboration capability for plotting and discussion functions. In the multiuser detection module, yolov2 is used for multiuser detection. The augmented reality hardware module is mainly composed of computers and hololens. Through the combination of hardware and software, a three-dimensional virtual sand table display of an industrial park is realized. The test results show that the performance of the designed system is good and can meet the design requirements. © 2021 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

3DS: An Efficient DPDK-based data Distribution Service for Distributed Real-time Applications

3DS: An Efficient DPDK-based Data Distribution Service for D...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Tianyu Xu Xianzhang Chen Changze Wu Jiapin Wang Rongwei Zheng Duo Liu Yujuan Tan Ao Ren Jian Li College of Computer Science Chongqing University Chongqing China School of Big Data and Software Engineering Chongqing University Chongqing China School of Electrical Engineering Chongqing University Chongqing China

data Distribution Service (DDS) is a widely-used middleware for data transmission in distributed real-time applications, such as autonomous vehicles and robotics. However, the communication of existing DDS middlewares generally relies on the network stacks of the operating system, which brings long latency to the real-time applications. In this paper, we propose a DPDK-based DDS, dubbed 3DS, to improve the performance of communication of DDS middlewares. First, 3DS reduces the latency of communication between distributed real-time applications by avoiding the latency of kernel. Second, 3DS reduces the overhead of dynamic memory allocation and deallocation by a reserved memory pool. Finally, 3DS adopts a thread-exclusive CPU model to reduce the resource contention between threads. We implement and evaluate 3DS on real systems running Linux. The experimental results show that 3DS reduces 44% of the communication latency over FastDDS, which is the state-of-the-art DDS middleware used by ROS2. Moreover, the throughput of data transfer in 3DS can be 1.51 times that of FastDDS.

关键词： Three-dimensional displays Smart cities Instruction sets Distributed databases Throughput Real-time systems Virtual machining

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：