检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Wei, Xiaohui Zhou, Changbao Yue, Hengshan Zhou, Joey Tianyi College of Computer Science and Technology Jilin University Jilin Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Jilin Changchun130012 China Singapore138632 Singapore Singapore138632 Singapore

As an architectural CNN accelerator integrated into NVIDIA's GPUs, existing research mainly focus on improving the performance of Tensor Core. However, the highly integrated Tensor Cores are vulnerable to transient faults (i.e., soft errors), causing catastrophic consequences in safety-critical applications like automatic driving. Thus, it is imperative to estimate the reliability of CNNs on Tensor Cores. However, it is expensive to obtain a statistically significant resilience profile of CNNs on Tensor Cores with the existing fault injection(FI)-based reliability estimation methods. To this end, we build TC-SEPM to predict the error resilience of CNNs on Tensor Cores instead of FI methods. To ensure the accuracy of TC-SEPM, we first investigate resilience-related features from microarchitecture and program perspectives. Then, leveraging these heuristic features, we train machine learning models to learn the hidden relationship between error resilience and the investigated features, enabling us to predict the impact of soft errors in Tensor Cores on CNN output. Experimental results show that TC-SEPM achieves high accuracy for individual soft error resiliency prediction and overall program resilience estimation while its overhead is only 1/27 of FI methods. Additionally, TC-SEPM can provide valuable insights for programmers or architects to design more robust CNN models on Tensor Cores. © 2023, The Authors. All rights reserved.

关键词： Error correction

来源：评论

学校读者我要写书评

暂无评论

A Novel Local Search Algorithm Based on Connectivity Method and Vertex Penalty Mechanism for Minimum Weighted Connected Dominating Set Problem

SSRN

引用

SSRN 2024年

作者： Li, Ruizhi He, Jintao Yin, Minghao Hu, Shuli Ding, Nan Jilin University of Finance and Economics Changchun130117 China Northeast Normal University Changchun130117 China Business Big Data Research Center of Jilin Province Changchun130117 China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun130012 China

The minimum weighted connected dominating set problem is a classical NP-hard problem with wide applications in practice. In this paper, an efficient local search algorithm is proposed to solve this problem. In this algorithm, firstly, an initial solution construction method based on greedy randomized adaptive strategy is adopted, which can balance the quality and the diversity of the initial solutions. Second, two new scoring functions, Ascore and Cscore, are proposed to increase the diversity of deleted vertices. Third, a new connectivity method is proposed so that the algorithm no longer relies on the shortest path between two connected components. Fourth, a vertex penalty mechanism is introduced, which helps the algorithm to jump out of the local optimum effectively. Fifth, two scoring functions, Ascore and Cscore, are combined with the vertex penalty mechanism to propose an effective vertex selection method, which helps the algorithm to select suitable vertices to be added to or removed from the current candidate solution. Finally, the propsoed local search algorithm is compared with seven state-of-the-art algorithms on three types of benchmark instances. The experimental results show that the algorithm exhibits better performance on these three types of classical benchmark instances. © 2024, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Independent and Collaborative Demosaicking Neural Networks 5

Independent and Collaborative Demosaicking Neural Networks

引用

5th ACM International Conference on Multimedia in Asia, MMAsia 2023

作者： Niu, Yan Zhang, Lixue Li, Chenlai State Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of Education College of Computer Science and Technology Jilin University Jilin Changchun China College of Computer Science and Technology Jilin University Changchun China School of Artificial Intelligence Shenzhen Polytechnic University Shenzhen China

ISBN: (纸本)9798400702051

Existing demosaicking neural models generally reconstruct the red, green and blue channels by one unified network. This has the advantage of allowing the RGB channels to share latent features. However, it is unnoticed that the training samples are severely unbalanced among the three channels. As a consequence, a unified model trained to fit the red or blue sample distributions is prone to under-fit the green samples. In this paper, we demonstrate the existence of such conflicts, and analyze the reason behind this phenomenon. To solve this disadvantage, we decouple the traditional three-in-one demosaicking to three independent but collaborative sub-tasks, respecting the distribution of samples in each spectrum. We show that, by our decoupling strategy, a very simple architecture can achieve high accuracy with high efficiency. For substantiation, we construct a model that has merely 1.3M parameters in total, and compares its accuracy to state of the art methods of similar or larger model size, across a wide variety of benchmark datasets. The proposed independent and collaborative architecture gains performance improvement over comparable models in both accuracy and inference time. © 2023 Copyright held by the owner/author(s).

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Traffic jam prediction based on analysis of residents spatial activities

Traffic jam prediction based on analysis of residents spatia...

引用

2020 International Conference on Computer Information and Big Data Applications, CIBDA 2020

作者： Lv, Zhijin Fu, Hao Tang, Wei Chen, Xiaoxu College of Software Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Changchun130012 China

ISBN: (纸本)9781728198378

The prediction of urban traffic congestion has always been one of the important contents in the research of intelligent transportation systems. The difficulty in predicting urban traffic congestion is that urban traffic operation is essentially a collection of spatial activity planning for residents under certain conditions. The huge group of residents themselves has great complexity and uncertainty. Traditional neural networks mostly focus on road characteristic data and road condition data, and lack of in-depth exploration of the fundamental factors of traffic congestion for residents' travel. So we propose a traffic congestion prediction model based on the analysis of residents' spatial activities. Starting from the residents' activities, the simulation of urban traffic operation conditions can more realistically reflect the traffic congestion situation of the city at specific times and roads, and quickly generate model results. The experimental results show that the model analyzed by residents' spatial activities runs fast and has high prediction accuracy. The results are in line with the actual situation and have strong practical value. © 2020 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

SpatioTemporal Learning for Human Pose Estimation in Sparsely-Labeled Videos

arXiv

引用

arXiv 2025年

作者： Jiao, Yingying Wang, Zhigang Wu, Sifan Fan, Shaojing Liu, Zhenguang Xu, Zhuoyue Wu, Zheqi College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China College of Computer Science and Technology Zhejiang Gongshang University China School of Computing National University of Singapore Singapore The State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China

Human pose estimation in videos remains a challenge, largely due to the reliance on extensive manual annotation of large datasets, which is expensive and labor-intensive. Furthermore, existing approaches often struggle to capture long-range temporal dependencies and overlook the complementary relationship between temporal pose heatmaps and visual features. To address these limitations, we introduce STDPose, a novel framework that enhances human pose estimation by learning spatiotemporal dynamics in sparsely-labeled videos. STDPose incorporates two key innovations: 1) A novel Dynamic-Aware Mask to capture long-range motion context, allowing for a nuanced understanding of pose changes. 2) A system for encoding and aggregating spatiotemporal representations and motion dynamics to effectively model spatiotemporal relationships, improving the accuracy and robustness of pose estimation. STDPose establishes a new performance benchmark for both video pose propagation (i.e., propagating pose annotations from labeled frames to unlabeled frames) and pose estimation tasks, across three large-scale evaluation datasets. Additionally, utilizing pseudo-labels generated by pose propagation, STDPose achieves competitive performance with only 26.7% labeled data. Copyright © 2025, The Authors. All rights reserved.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Independently keypoint Learning for Small Object Semantic Correspondence

SSRN

引用

SSRN 2024年

作者： Jin, Hailong Li, Huiying Jilin University College of Computer Science and Technology Jilin Province Changchun China Key Laboratory of Symbol Computation and Knowledge Engineering Jilin University Changchun130012 China

Semantic correspondence remains a challenging task for establishing correspondences between a pair of images with the same category or similar scenes due to the large intra-class appearance. In this paper, we introduce a novel problem called 'Small Object Semantic Correspondence (SOSC).' This problem is challenging due to the close proximity of keypoints associated with small objects, which results in the fusion of these respective features. It is difficult to identify the corresponding key points of the fused features, and it is also difficult to be recognized. To address this challenge, we propose the keypoint Bounding box-centered Cropping (KBC) method, which aims to increase the spatial separation between keypoints of small objects, thereby facilitating independent learning of these keypoints. The KBC method is seamlessly integrated into our proposed inference pipeline and can be easily incorporated into other methodologies, resulting in significant performance enhancements. Additionally, we introduce a novel framework, named KBCNet, which serves as our baseline model. KBCNet comprises a Cross-Scale Feature Alignment (CSFA) module and an efficient 4D convolutional decoder. The CSFA module is designed to align multi-scale features, enriching keypoint representations by integrating fine-grained features and deep semantic features. Meanwhile, the 4D convolutional decoder, based on efficient 4D convolution, ensures efficiency and rapid convergence. To empirically validate the effectiveness of our proposed methodology, extensive experiments are conducted on three widely used benchmarks: PF-PASCAL, PF-WILLOW, and SPair-71k. Our KBC method demonstrates a substantial performance improvement of 7.5\% on the SPair-71K dataset, providing compelling evidence of its efficacy. © 2024, 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

2D-3D Feature Co-Embedding Network with Sparse Annotation for 3D Medical Image Segmentation

2D-3D Feature Co-Embedding Network with Sparse Annotation fo...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Mingzhu Zhu Shuyu Guo Ziwei Wang Jianhang Jiao Tian Bai College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China College of Software Jilin University Changchun China Department of Orthopedics The Second Norman Bethune Hospital of Jilin University Changchun China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Supervised methods on 3D medical image segmentation need large amounts of annotated data, but annotating is time-consuming. Also, existing 3D segmentation methods capture more global structural information but overlook local detailed features, which negatively impacts the segmentation of small tissues. In this paper, we propose a novel weakly-supervised 2D-3D Feature Co-Embedding Network (2D-3D CoENet) that includes 2D and 3D encoding layers, simultaneously extracting 2D local detailed and 3D global structural features. To reduce annotation costs, we use fewer labeled slices as ground truth and pseudo-labels are generated by 2D-3D CoENet for other slices. Additionally, multi-view learning is introduced to capture more 2D local detailed information, and a Multi-view Semantic Consistency loss (MSC loss) is proposed to constrain features from multiple perspectives. To further enhance the local detailed texture features, we propose an Edge Enhancement Module (EEM) in the 3D segmentation network to enhance the edge detail features. Our experimental results on the SKI10 dataset and OAI ZIB dataset demonstrate that our method outperforms the SOTA weakly-supervised segmentation methods. Moreover, our approach achieves results that are comparable to the fully-supervised upper bound results.

关键词： Image segmentation Three-dimensional displays Costs Upper bound Annotations Image edge detection Semantics Feature extraction Encoding Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Learning Generalizable Agents via Saliency-Guided Features Decorrelation

arXiv

引用

arXiv 2023年

作者： Huang, Sili Sun, Yanchao Hu, Jifeng Guo, Siyuan Chen, Hechang Chang, Yi Sun, Lichao Yang, Bo Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education China School of Artificial Intelligence Jilin University China Department of Computer Science University of Maryland College Park United States Lehigh University BethlehemPA United States

In visual-based Reinforcement Learning (RL), agents often struggle to generalize well to environmental variations in the state space that were not observed during training. The variations can arise in both task-irrelevant features, such as background noise, and task-relevant features, such as robot configurations, that are related to the optimal decisions. To achieve generalization in both situations, agents are required to accurately understand the impact of changed features on the decisions, i.e., establishing the true associations between changed features and decisions in the policy model. However, due to the inherent correlations among features in the state space, the associations between features and decisions become entangled, making it difficult for the policy to distinguish them. To this end, we propose Saliency-Guided Features Decorrelation (SGFD) to eliminate these correlations through sample reweighting. Concretely, SGFD consists of two core techniques: Random Fourier Functions (RFF) and the saliency map. RFF is utilized to estimate the complex non-linear correlations in high-dimensional images, while the saliency map is designed to identify the changed features. Under the guidance of the saliency map, SGFD employs sample reweighting to minimize the estimated correlations related to changed features, thereby achieving decorrelation in visual RL tasks. Our experimental results demonstrate that SGFD can generalize well on a wide range of test environments and significantly outperforms state-of-the-art methods in handling both task-irrelevant variations and task-relevant variations. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Structure- and Logic-Aware Heterogeneous Graph Learning for Recommendation

Structure- and Logic-Aware Heterogeneous Graph Learning for ...

引用

International Conference on Data engineering

作者： Anchen Li Bo Yang Huan Huo Farookh Khadeer Hussain Guandong Xu College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education China Aalto University Espoo Finland School of Computer Science University of Technology Sydney Sydney Australia Education University of Hong Kong Hong Kong China

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Recently, there has been a surge in recommendations based on heterogeneous information networks (HINs), attributed to their ability to integrate complex and rich semantics. Despite this advancement, most HIN-based recommenders overlook two critical aspects. First, they often fail to consider HIN's heterophily nature, hindering the capture of non-local structures in HINs. Second, most methods lack the capability for logical reasoning. In this paper, we propose a novel structure- and logic-aware heterogeneous graph learning framework for recommender systems (SLHRec). Our SLHRec contains a structure-aware module and a logic-aware module. The former uses network geometry to construct non-local neighborhoods for nodes in HINs, and then introduces a graph neural network to integrate constructed neighbors for modeling the heterophily of HINs. The logic-aware module uses the Markov logic network (MLN) to infuse logic rules into heterogeneous graph learning, thereby boosting logic reasoning in recommendations. Furthermore, we utilize contrastive learning to model cooperative signals between modules, enabling them to complement each other. In the prediction stage, both modules contribute to generating recommendations. Compared with several strong recommender baselines, our SLHRec achieves superior performance on four real-world datasets.

关键词： Geometry Semantics Contrastive learning Data engineering Boosting Cognition Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

HVIS: A Human-like Vision and Inference System for Human Motion Prediction

arXiv

引用

arXiv 2025年

作者： Lyu, Kedi Chen, Haipeng Liu, Zhenguang Yin, Yifang Lin, Yukang Jiao, Yingying College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Institute of Blockchain and Data Security Hangzhou China A*STAR Singapore Tsinghua Shenzhen International Graduate School Nanshan District Shenzhen China

Grasping the intricacies of human motion, which involve perceiving spatio-temporal dependence and multi-scale effects, is essential for predicting human motion. While humans inherently possess the requisite skills to navigate this issue, it proves to be markedly more challenging for machines to emulate. To bridge the gap, we propose the Human-like Vision and Inference System (HVIS) for human motion prediction, which is designed to emulate human observation and forecast future movements. HVIS comprises two components: the human-like vision encode (HVE) module and the human-like motion inference (HMI) module. The HVE module mimics and refines the human visual process, incorporating a retina-analog component that captures spatiotemporal information separately to avoid unnecessary crosstalk. Additionally, a visual cortex-analogy component is designed to hierarchically extract and treat complex motion features, focusing on both global and local features of human poses. The HMI is employed to simulate the multi-stage learning model of the human brain. The spontaneous learning network simulates the neuronal fracture generation process for the adversarial generation of future motions. Subsequently, the deliberate learning network is optimized for hard-to-train joints to prevent misleading learning. Experimental results demonstrate that our method achieves new state-of-the-art performance, significantly outperforming existing methods by 19.8% on Human3.6M, 15.7% on CMU Mocap, and 11.1% on G3D. © 2025, CC BY.

关键词： Motion estimation

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：