检索结果-内蒙古大学图书馆

D4M: Dataset Distillation via Disentangled Diffusion Model

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Su, Duo Hou, Junjie Gao, Weizhi Tian, Yingjie Tang, Bowen School of Computer Science and Technology UCAS United Kingdom Sino-Danish College UCAS United Kingdom Department of Computer Science NCSU United States School of Economics and Management UCAS United Kingdom Research Center on Fictitious Economy and Data Science CAS China Key Laboratory of Big Data Mining and Knowledge Management CAS China MOE Social Science Laboratory of Digital Economic Forecasts and Policy Simulation UCAS United Kingdom Institute of Computing Technology CAS China

Dataset distillation offers a lightweight synthetic dataset for fast network training with promising test accuracy. To imitate the performance of the original dataset, most approaches employ bi-level optimization and the distillation space relies on the matching architecture. Nevertheless, these approaches either suffer significant computational costs on large-scale datasets or experience performance decline on cross-architectures. We advocate for designing an economical dataset distillation framework that is independent of the matching architectures. With empirical observations, we argue that constraining the consistency of the real and synthetic image spaces will enhance the cross-architecture generalization. Motivated by this, we introduce Dataset Distillation via Disentangled Diffusion Model (D4M), an efficient framework for dataset distillation. Compared to architecture-dependent methods, D4M employs latent diffusion model to guarantee consistency and incorporates label information into category prototypes. The distilled datasets are versatile, eliminating the need for repeated generation of distinct datasets for various architectures. Through comprehensive experiments, D4M demonstrates superior performance and robust generalization, surpassing the SOTA methods across most aspects. Copyright © 2024, The Authors. All rights reserved.

关键词： Distillation

Self-supervised 3D Point Cloud Completion via Multi-view Adversarial Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wu, Lintai Cheng, Xianjing Xu, Yong Zeng, Huanqiang Hou, Junhui Bio-Computing Research Center Harbin Institute of Technology Shenzhen Guangdong Shenzhen518055 China The Department of Computer Science City University of Hong Kong Hong Kong School of Computer Science and Technology Harbin Institute of Technology Shenzhen Guangdong Shenzhen518055 China Department of Computer Science City University of Hong Kong Hong Kong Shenzhen Key Laboratory of Visual Object Detection and Recognition Guangdong Shenzhen518055 China School of Engineering Huaqiao University Quanzhou362021 China School of Information Science and Engineering Huaqiao University Xiamen361021 China

In real-world scenarios, scanned point clouds are often incomplete due to occlusion issues. The task of self-supervised point cloud completion involves reconstructing missing regions of these incomplete objects without the supervision of complete ground truth. Current self-supervised methods either rely on multiple views of partial observations for supervision or overlook the intrinsic geometric similarity that can be identified and utilized from the given partial point clouds. In this paper, we propose MAL-SPC, a framework that effectively leverages both region-level and category-specific geometric similarities to complete missing structures. Our MAL-SPC does not require any 3D complete supervision and only necessitates a single partial point cloud for each object. Specifically, we first introduce a Pattern Retrieval Network to retrieve similar position and curvature patterns between the partial input and the predicted shape, then leverage these similarities to densify and refine the reconstructed results. Additionally, we render the reconstructed complete shape into multi-view depth maps and design an adversarial learning module to learn the geometry of the target shape from category-specific single-view depth images. To achieve anisotropic rendering, we design a density-aware radius estimation algorithm to improve the quality of the rendered images. Our MAL-SPC yields the best results compared to current state-of-the-art methods. We will make the source code publicly available at https://***/ltwu6/malspc. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

Towards an Ontology of Traceable Impact Management in the Food Supply Chain

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Gajderowicz, Bart Fox, Mark S. Gao, Yongchao Urban Data Centre School of Cities University of Toronto Toronto Canada Key Laboratory of Computing Power Network and Information Security Shandong Computer Science Center Qilu University of Technology Shandong Academy of Sciences Jinan China

The pursuit of quality improvements and accountability in the food supply chains, especially how they relate to food-related outcomes, such as hunger, has become increasingly vital, necessitating a comprehensive approach that encompasses product quality and its impact on various stakeholders and their communities. Such an approach offers numerous benefits in increasing product quality and eliminating superfluous measurements while appraising and alleviating the broader societal and environmental repercussions. A traceable impact management model (TIMM) provides an impact structure and a reporting mechanism that identifies each stakeholder’s role in the total impact of food production and consumption stages. The model aims to increase traceability’s utility in understanding the impact of changes on communities affected by food production and consumption, aligning with current and future government requirements, and addressing the needs of communities and consumers. This holistic approach is further supported by an ontological model that forms the logical foundation and a unified terminology. By proposing a holistic and integrated solution across multiple stakeholders, the model emphasizes quality and the extensive impact of championing accountability, sustainability, and responsible practices with global traceability. With these combined efforts, the food supply chain moves toward a global tracking and tracing process that not only ensures product quality but also addresses its impact on a broader scale, fostering accountability, sustainability, and responsible food production and consumption. © 2025, CC BY.

关键词：

CLDG: Contrastive Learning on Dynamic Graphs 39

学校读者我要写书评

暂无评论

CLDG: Contrastive Learning on Dynamic Graphs

39th IEEE International Conference on Data Engineering, ICDE 2023

作者： Xu, Yiming Shi, Bin Ma, Teng Dong, Bo Zhou, Haoyi Zheng, Qinghua Xi'an Jiaotong University Department of Computer Science and Technology China Xi'an Jiaotong University Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering China Xi'an Jiaotong University Department of Distance Education China Beihang University School of Software China Beihang University Advanced Innovation Center for Big Data and Brain Computing China

ISBN: (纸本)9798350322279

The graph with complex annotations is the most potent data type, whose constantly evolving motivates further exploration of the unsupervised dynamic graph representation. One of the representative paradigms is graph contrastive learning. It constructs self-supervised signals by maximizing the mutual information between the statistic graph's augmentation views. However, the semantics and labels may change within the augmentation process, causing a significant performance drop in downstream tasks. This drawback becomes greatly magnified on dynamic graphs. To address this problem, we designed a simple yet effective framework named CLDG. Firstly, we elaborate that dynamic graphs have temporal translation invariance at different levels. Then, we proposed a sampling layer to extract the temporally-persistent signals. It will encourage the node to maintain consistent local and global representations, i.e., temporal translation invariance under the timespan views. The extensive experiments demonstrate the effectiveness and efficiency of the method on seven datasets by outperforming eight unsupervised state-of-the-art baselines and showing competitiveness against four semi-supervised methods. Compared with the existing dynamic graph method, the number of model parameters and training time is reduced by an average of 2,001.86 times and 130.31 times on seven datasets, respectively. The code and data are available at: https://***/yimingxu24/CLDG. © 2023 IEEE.

关键词： Graph neural networks

Reinforcing Spatiotemporal Correlation: Learning Comprehensive Feature Representations for Gait Recognition

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Chen, Jianyu Wang, Zhongyuan Zeng, Kangli Zou, Qin Liang, Chao Xu, Zengmin Wu, Gang National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China School of Mathematics and Computing Science Guilin University of Electronic Technology Guilin541004 China College of Information Engineering Tarim University Alar843300 China Shenzhen518060 China

Gait recognition attracts extensive attention as biotechnology for identifying subjects from a distance without their cooperation. Since gait is not easily camouflaged and successive motion trajectories facilitate the identification of subjects, capturing critical temporal information is particularly important for gait recognition. Compared with architectures that extract temporal features individually and then perform late fusion, 3D CNNs are more suitable for extracting continuous relationships between frames in gait sequences. Hence, in this paper, we propose a novel 3D architecture called robust spatiotemporal 3D convolutional neural network (RST3D) to collaboratively extract spatiotemporal correlations in gait sequences. Specifically, we propose a full-scale 3D convolutional block that fully considers the orthogonal relationships in multiple dimensions based on the original 3D convolution, thus it can extract more potential gait spatiotemporal features. Next, to further enhance the temporal modeling capability of the network, we propose a temporal pyramidal attention block to capture the most discriminative motion representations from different ranges of gait silhouettes. Experiments on CASIA-B, OUMVLP, GREW and Gait3D datasets demonstrate that our proposed method outperforms the state-of-the-art gait methods. Furthermore, compared to the existing 3D CNN-based gait recognition methods, our approach exhibits superior performance in several complex gait conditions. © 2024, The Authors. All rights reserved.

关键词： Convolution

SMOTE Oversampling and Near Miss Undersampling Based Diabetes Diagnosis from Imbalanced Dataset with XAI Visualization

学校读者我要写书评

暂无评论

SMOTE Oversampling and Near Miss Undersampling Based Diabete...

IEEE Symposium on computers and Communications (ISCC)

作者： Nasim Mahmud Nayan Ashraful Islam Muhammad Usama Islam Eshtiak Ahmed Mohammad Mobarak Hossain Md Zahangir Alam Department of Computer Science and Engineering University of Information Technology and Sciences Bangladesh Center for Computational and Data Sciences Independent University Bangladesh Department of Computer Science and Engineering Independent University Bangladesh School of Computing and Informatics University of Louisiana at Lafayette USA Department of Computer Science and Engineering Daffodil International University Bangladesh

This study investigated the predictive ability of ten different machine learning (ML) models for diabetes using a dataset that was not evenly distributed. Additionally, the study evaluated the effectiveness of two oversampling and undersampling methods, namely the Synthetic Minority Oversampling Technique (SMOTE) and the Near-Miss algorithm. Explainable Artificial Intelligence (XAI) techniques were employed to enhance the interpretability of the model's predictions. The results indicate that the extreme gradient boosting (XGB) model combined with SMOTE oversampling technique exhibited the highest accuracy and an F1-score of 99% and 1.00 respectively. Furthermore, the utilization of XAI methods increased the dependability of the model's decision-making process, rendering it more appropriate for clinical use. These results imply that integrating XAI with ML and oversampling techniques can enhance the early detection and management of diabetes, leading to better diagnosis and intervention.

关键词：

Cross-lingual Prompting: Improving Zero-shot Chain-of-Thought Reasoning across Languages

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Qin, Libo Chen, Qiguang Wei, Fuxuan Huang, Shijue Che, Wanxiang School of Computer Science and Engineering Central South University China Research Center for Social Computing and Information Retrieval Colombia Harbin Institute of Technology China Harbin Institute of Technology Shenzhen China

Chain-of-thought (CoT) is capable of eliciting models to explicitly generate reasoning paths, thus promoting reasoning accuracy and attracting increasing attention. Specifically, zero-shot CoT achieves remarkable improvements in a wide range of reasoning tasks by simply instructing the LLM with the prompt "Let’s think step by step!". Despite the success of zero-shot CoT, the existing zero-shot prompting techniques remain limited to a single language, making it challenging to generalize to other languages and hindering global development. In this work, we introduce cross-lingual prompting (CLP), aiming to improve zero-shot CoT reasoning across languages. Specifically, CLP consists of two main components: (1) cross-lingual alignment prompting and (2) task-specific solver prompting. The cross-lingual alignment prompting is responsible for aligning representations across different languages, whereas the task-specific solver prompting is used to generate the final chain of thoughts and results for the reasoning task. In addition, we further introduce cross-lingual self-consistent prompting (CLSP) to ensemble different reasoning paths across languages. Our experimental evaluations on several benchmarks demonstrate that CLP and CLSP significantly outperform the existing prompting methods and achieve state-of-the-art performance. We hope this work will inspire further breakthroughs in cross-lingual CoT. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

OpenLS-DGF: An Adaptive Open-Source Dataset Generation Framework for Machine Learning Tasks in Logic Synthesis

学校读者我要写书评

暂无评论

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Ni, Liwei Wang, Rui Liu, Miao Meng, Xingyu Lin, Xiaoze Liu, Junfeng Luo, Guojie Chu, Zhufei Qian, Weikang Yang, Xiaoyan Xie, Biwei Li, Xingquan Li, Huawei Chinese Academy of Sciences State Key Lab of Processors Institute of Computing Technology Beijing100190 China Pengcheng Laboratory Shenzhen518055 China University of Chinese Academy of Sciences Beijing101408 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China University of Chinese Academy of Sciences School of Computer Science and Technology Beijing100049 China Peking University School of Computer Science Center for Energy-Efficient Computing and Applications Beijing100871 China Ninbo University Faculty of Electrical Engineering and Computer Science Ninbo315211 China Shanghai Jiao Tong University University of Michigan-Shanghai Jiao Tong University Joint Institute MoE Key Laboratory of Artificial Intelligence Shanghai200240 China Hangzhou Dianzi University School of Electronics and Information Engineering Hangzhou311121 China

This paper introduces OpenLS-DGF, an adaptive logic synthesis dataset generation framework, to enhance machine learning (ML) applications within the logic synthesis process. Previous dataset generation flows were tailored for specific tasks or lacked integrated ML capabilities. While OpenLS-DGF supports various machine learning tasks by encapsulating the three fundamental steps of logic synthesis: Boolean representation, logic optimization, and technology mapping. It preserves the original information in both Verilog and ML-friendly GraphML formats. The Verilog files offer semi-customizable capabilities, enabling researchers to insert additional steps and incrementally refine the generated dataset. Furthermore, OpenLS-DGF includes an adaptive circuit engine that facilitates the final dataset management and downstream tasks. The generated OpenLS-D-v1 dataset comprises 46 combinational designs from established benchmarks, totaling over 966,000 Boolean circuits. OpenLS-D-v1 supports integrating new data features, making it more versatile for new tasks. This paper demonstrates the versatility of OpenLS-D-v1 through four distinct downstream tasks: circuit classification, circuit ranking, quality of results (QoR) prediction, and probability prediction. Each task is chosen to represent essential steps of logic synthesis, and the experimental results show the generated dataset from OpenLSDGF achieves prominent diversity and applicability. The source code and datasets are available at https://***/Logic-Factory/ACE/blob/master/OpenLS-DGF. © 1982-2012 IEEE.

关键词： Information management

Take a Prior from Other Tasks For Severe Blur Removal

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Wang, Pei Xue, Danna Zhu, Yu Sun, Jinqiu Yan, Qingsen Yoon, Sung-Eui Zhang, Yanning School of Computer Science and Engineering Northwestern Polytechnical University Xi’an China School of Astronautics Northwestern Polytechnical University Xi’an China Computer Vision Center Universitat Autònoma de Barcelona Barcelona Spain School of Computing Korea Advanced Institute of Science and Technology Daejeon Korea Republic of

Recovering clear structures from severely blurry inputs is a challenging problem due to the large movements between the camera and the scene. Although some works apply segmentation maps on human face images for deblurring, they cannot handle natural scenes because objects and degradation are more complex, and inaccurate segmentation maps lead to a loss of details. For general scene deblurring, the feature space of the blurry image and corresponding sharp image under the high-level vision task is closer, which inspires us to rely on other tasks (e.g. classification) to learn a comprehensive prior in severe blur removal cases. We propose a cross-level feature learning strategy based on knowledge distillation to learn the priors, which include global contexts and sharp local structures for recovering potential details. In addition, we propose a semantic prior embedding layer with multi-level aggregation and semantic attention transformation to integrate the priors effectively. We introduce the proposed priors to various models, including the UNet and other mainstream deblurring baselines, leading to better performance on severe blur removal. Extensive experiments on natural image deblurring benchmarks and real-world images, such as GoPro and RealBlur datasets, demonstrate our method's effectiveness and generalization ability. © 2023, The Authors. All rights reserved.

关键词： Semantics