检索结果-内蒙古大学图书馆

13th International Conference on intelligent Control and information processing, ICICIP 2025

作者： Li, Jiahao Wang, Zhongshuai Ghazali, Kamarul Hawari Bin Yan, Suqing Lan, Rushi Sun, Xiyan Luo, Xiaonan Guangxi Key Lab. of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin541004 China Centre for Advanced Industrial Technology University of Malaysia Pahang Al-Sultan Abdullah Pahang Pekan26600 Malaysia Int. Joint Research Lab. of Spatio-temporal Information and Intelligent Location Services Guilin University of Electronic Technology Guilin541004 China

ISBN: (纸本)9798331516147

Privacy-preserving image generation is particularly crucial in fields like healthcare, where data are both sensitive and limited. However, effective privacy preservation often compromises the visual quality and utility of the generated images due to privacy budget constraints. To address this issue, in this paper, We propose a novel network architecture, IRSEnet, which combines multi-scale feature extraction technology and residual channel attention mechanisms, aiming to enhance the visual quality of generated images and improve the performance of downstream classification tasks under differential privacy. The differential privacy mechanism ensures the security of sensitive data during training, while the multi-scale feature extraction module enhances feature extraction capabilities through parallel convolutional layers at multiple scales. Additionally, the channel attention module dynamically adjusts channel weights to focus on the most discriminative features. Experimental results demonstrate that this model significantly improves the utility of generated images and the accuracy of downstream classification tasks while preserving privacy. Future work will explore the application of this approach on larger datasets and across more diverse tasks. © 2025 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation 38

AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmenta...

引用

38th Conference on Neural information processing Systems, NeurIPS 2024

作者： Han, Boyu Xu, Qianqian Yang, Zhiyong Bao, Shilong Wen, Peisong Jiang, Yangbangyan Huang, Qingming Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China School of Computer Science and Tech. University of Chinese Academy of Sciences China Peng Cheng Laboratory China Key Laboratory of Big Data Mining and Knowledge Management CAS China

The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have been proposed to improve model performance under long-tail distributions. In this paper, we explore AUC optimization methods in the context of pixel-level long-tail semantic segmentation, a much more complicated scenario. This task introduces two major challenges for AUC optimization techniques. On one hand, AUC optimization in a pixel-level task involves complex coupling across loss terms, with structured inner-image and pairwise inter-image dependencies, complicating theoretical analysis. On the other hand, we find that mini-batch estimation of AUC loss in this case requires a larger batch size, resulting in an unaffordable space complexity. To address these issues, we develop a pixel-level AUC loss function and conduct a dependency-graph-based theoretical analysis of the algorithm's generalization ability. Additionally, we design a Tail-Classes Memory Bank (T-Memory Bank) to manage the significant memory demand. Finally, comprehensive experiments across various benchmarks confirm the effectiveness of our proposed AUCSeg method. The code is available at https://***/boyuh/AUCSeg. © 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

Improving Bert Fine-Tuning via Stabilizing Cross-Layer Mutual information 48

Improving Bert Fine-Tuning via Stabilizing Cross-Layer Mutua...

引用

48th IEEE International Conference on Acoustics, Speech and Signal processing, ICASSP 2023

作者： Li, Jicun Li, Xingjian Wang, Tianyang Wang, Shi Cao, Yanan Xu, Chengzhong Dou, Dejing Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Big Data Lab Baidu Research China University of Alabama Birmingham United States Institute of Information Engineering Chinese Academy of Sciences China State Key Lab of Iotsc University of Macau China

ISBN: (纸本)9781728163277

Fine-tuning pre-trained language models, such as BERT, has shown enormous success among various NLP tasks. Though simple and effective, the process of fine-tuning has been found unstable, which often leads to unexpected poor performance. To increase stability and generalizability, most existing works resort to maintaining the parameters or representations of pre-trained models during fine-tuning. Nevertheless, very little work explores mining the reliable part of pre-learned information that can help to stabilize fine-tuning. To address this challenge, we introduce a novel solution in which we fine-tune BERT with stabilized cross-layer mutual information. Our method aims to preserve the reliable behaviors of cross-layer information propagation, instead of preserving the information itself, of the pre-trained model. Therefore, our method circumvents the domain conflicts between pre-trained and target tasks. We conduct extensive experiments with popular pre-trained BERT variants on NLP datasets, demonstrating the universal effectiveness and robustness of our method. © 2023 IEEE.

关键词： Fine-tuning Stability Mutual information Pre-trained Language Model

来源：评论

学校读者我要写书评

暂无评论

A Flexible Knowledge Graph Error Detection Framework Combined with Semantic information 12th

A Flexible Knowledge Graph Error Detection Framework Combine...

引用

12th CCF Conference on BigData, BigData 2024

作者： Zhao, Yangwu Liu, Yang Ao, Xiang He, Qing Henan Institute of Advanced Technology Zhengzhou University Zhengzhou China Beijing China Key Lab of Intelligent Information Processing Institute of Computing Technology CAS Beijing China

ISBN: (纸本)9789819610235

Knowledge graphs (KGs) are extensively utilized in numerous applications, including question-answering systems and recommender systems. However, knowledge graphs are often constructed through web crawling or crowdsourcing, leading to errors in the data. The task of knowledge graph error detection aims to identify inaccurate triplets in KGs and has received substantial attention in recent years. However, the majority of current error detection methods overlook the semantic information of the triplets, which can be vital for accurate error detection. In this paper, we introduce a Flexible Knowledge Graph Error Detection Framework that integrates Semantic information (FKED), which combines both structural and semantic information to detect errors within the knowledge graph. FKED first extracts the structural information of KGs using a graph embedding model. Next, FKED employs a pre-trained language model (PLM) to extract semantic information from the triplets. Then the structural and semantic information are combined to detect errors within the knowledge graph. FKED can be flexibly added to other structure-based error detection models, enhancing their capabilities in downstream tasks of knowledge graphs. We assess FKED using two benchmark datasets: FB15k-237 and WN18RR. Experimental results indicate that our method is both superior and effective, substantially improving the performance of the base models. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

DMSS:An Attention-Based Deep Learning Model for High-Quality Mass Spectrometry Prediction

引用

Big Data Mining and Analytics 2024年第3期7卷 577-589页

作者： Yihui Ren Yu Wang Wenkai Han Yikang Huang Xiaoyang Hou Chunming Zhang Dongbo Bu Xin Gao Shiwei Sun Key Lab of Intelligent Information Processing Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190Chinaand with University of Chinese Academy of SciencesBeijing 100049China Syneron Technology Guangzhou 510000China College of Information and Electrical Engineering China Agricultural UniversityBeijing 100083China Computer Science Program ComputerElectrical and Mathematical Sciences and Engineering DivisionKing Abdullah University of Science and Technology(KAUST)Thuwal 23955-6900Kingdom of Saudi Arabia Insitute of Computing Technology Chinese Academy of SciencesBeijing 100190China with Western Institute of Computing Technology Chongqing 400000China

Accurate prediction of peptide spectra is crucial for improving the efficiency and reliability of proteomic analysis,as well as for gaining insight into various biological *** this study,we introduce Deep MS Simulator(DMSS),a novel attention-based model tailored for forecasting theoretical spectra in mass *** has undergone rigorous validation through a series of experiments,consistently demonstrating superior performance compared to current methods in forecasting theoretical *** superior ability of DMSS to distinguish extremely similar peptides highlights the potential application of incorporating our predicted intensity information into mass spectrometry search engines to enhance the accuracy of protein *** findings contribute to the advancement of proteomics analysis and highlight the potential of the DMSS as a valuable tool in the field.

关键词： mass spectrometry proteomics machine learning deep learning

来源：评论

学校读者我要写书评

暂无评论

Nested relation extraction with iterative neural network

引用

Frontiers of Computer Science 2021年第3期15卷 109-122页

作者： Yixuan CAO Dian CHEN Zhengqi XU Hongwei LI Ping LUO Key Lab of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing TechnologyCASBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China

Most existing researches on relation extraction focus on binary flat relations like Bomln relation between a Person and a *** a large portion of objective facts de-scribed in natural language are complex,especially in professional documents in fields such as finance and biomedicine that require precise *** example,“the GDP of the United States in 2018 grew 2.9%compared with 2017”describes a growth rate relation between two other relations about the economic index,which is beyond the expressive power of binary flat ***,we propose the nested relation extraction problem and formulate it as a directed acyclic graph(DAG)structure extraction ***,we propose a solution using the Iterative Neural Network which extracts relations layer by *** proposed solution achieves 78.98 and 97.89 FI scores on two nested relation extraction tasks,namely semantic cause-and-efFect relation extraction and formula ***,we observe that nested relations are usually expressed in long sentences where entities are mentioned repetitively,which makes the annotation difficult and ***,we extend our model to incorporate a mention-insensitive mode that only requires annotations of relations on entity concepts(instead of exact mentions)while preserving most of its *** mention-insensitive model performs better than the mention sensitive model when the random level in mention selection is higher than 0.3.

关键词： nested relation extraction mention insensitive relation iterative neural network

来源：评论

学校读者我要写书评

暂无评论

AlphaFold2 and its applications in the fields of biology and medicine

引用

Signal Transduction and Targeted Therapy 2023年第4期8卷 1630-1643页

作者： Zhenyu Yang Xiaoxi Zeng Yi Zhao Runsheng Chen West China Biomedical Big Data Center West China HospitalSichuan UniversityChengdu 610041China Key Laboratory of Intelligent Information Processing Advanced Computer Research CenterInstitute of Computing TechnologyChinese Academy of SciencesBeijing 100190China Key Laboratory of RNA Biology Center for Big Data Research in HealthInstitute of BiophysicsChinese Academy of SciencesBeijing 100101China Pingshan Translational Medicine Center Shenzhen Bay LaboratoryShenzhen 518118China

AlphaFold2(AF2)is an artificial intelligence(AI)system developed by DeepMind that can predict three-dimensional(3D)structures of proteins from amino acid sequences with atomic-level *** structure prediction is one of the most challenging problems in computational biology and chemistry,and has puzzled scientists for 50 *** advent of AF2 presents an unprecedented progress in protein structure prediction and has attracted much *** release of structures of more than 200 million proteins predicted by AF2 further aroused great enthusiasm in the science community,especially in the fields of biology and ***2 is thought to have a significant impact on structural biology and research areas that need protein structure information,such as drug discovery,protein design,prediction of protein function,et *** the time is not long since AF2 was developed,there are already quite a few application studies of AF2 in the fields of biology and medicine,with many of them having preliminarily proved the potential of *** better understand AF2 and promote its applications,we will in this article summarize the principle and system architecture of AF2 as well as the recipe of its success,and particularly focus on reviewing its applications in the fields of biology and *** of current AF2 prediction will also be discussed.

关键词： system fields Fold

来源：评论

学校读者我要写书评

暂无评论

ETS: An Error Tolerable System for Coreference Resolution 15

ETS: An Error Tolerable System for Coreference Resolution

引用

15th Conference on Computational Natural Language Learning, CoNLL 2011

作者： Xiong, Hao Song, Linfeng Meng, Fandong Liu, Yang Liu, Qun Lü, Yajuan Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing100190 China

ISBN: (纸本)9781937284084

This paper presents our error tolerable system for coreference resolution in CoNLL-2011(Pradhan et al., 2011) shared task (closed track). Different from most previous reported work, we detect mention candidates based on packed forest instead of single parse tree, and we use beam search algorithm based on the Bell Tree to create entities. Experimental results show that our methods achieve promising results on the development set. © 2011 Association for Computational Linguistics

关键词： Forestry

来源：评论

学校读者我要写书评

暂无评论

Tunable dipole–dipole interactions between nanoparticles levitated by two orthogonally polarized optical traps

引用

Photonics research 2024年第10期12卷 2139-2147页

作者： TONG LI MIAN WU PEITONG HE NAN LI ZHIMING CHEN ZHENHAI FU XIAOWEN GAO HUIZHU HU Research Center for Advanced Computational Sensing and Intelligent Processing Zhejiang LabHangzhou 310000China State Key Laboratory of Extreme Photonics and Instrumentation College of Optical Science and EngineeringZhejiang UniversityHangzhou 310027China Research Center for Frontier Fundamental Studies Zhejiang LabHangzhou 310000China

Arrays of optically levitated nanoparticles with fully tunable light-induced dipole–dipole interactions have emerged as a platform for fundamental research and sensing ***,previous experiments utilized two optical traps with identical polarization,leading to an interference ***,we demonstrate light-induced dipole–dipole interactions using two orthogonally polarized optical ***,we achieve control over the strength and polarity of the optical coupling by adjusting the polarization and propose a method to simultaneously and stably measure conservative and non-conservative coupling *** results provide a new scheme for exploring entanglement and topological phases in arrays of levitated nanoparticles.

关键词： dipole polarized conservative

来源：评论

学校读者我要写书评

暂无评论

FLIP-80M: 80 Million Visual-Linguistic Pairs for Facial Language-Image Pre-Training 24

FLIP-80M: 80 Million Visual-Linguistic Pairs for Facial Lang...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Li, Yudong Hou, Xianxu Dezhi, Zheng Shen, Linlin Zhao, Zhe School of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of AI and Advanced Computing Xi'an Jiaotong-Liverpool University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Tencent AI Lab Beijing China

ISBN: (纸本)9798400706868

While significant progress has been made in multi-modal learning driven by large-scale image-text datasets, there is still a noticeable gap in the availability of such datasets within the facial domain. To facilitate and advance the field of facial representation learning, we present FLIP-80M, a large-scale visual-linguistic dataset comprising over 80 million face images paired with text descriptions. FLIP-80M is constructed by leveraging the large openly available image-text-pair dataset LAION-5B and a mixed-method approach to filter face-related pairs from both visual and linguistic perspectives. Our curation process involves face detection, face caption classification, text de-noising, and synthesis-based image augmentation. As a result, FLIP-80M stands as the largest face-text dataset to date. To evaluate the potential of our dataset, we fine-tune the CLIP model using the proposed FLIP-80M, to create FLIP (Facial Language-Image Pretraining) and assess its representation capabilities across various downstream tasks. Our experiments demonstrate that our FLIP model achieves state-of-the-art results in a range of face analysis tasks, including face parsing, face alignment, and face attribute classification. The dataset and models are available at https://***/ydli-ai/FLIP. © 2024 ACM.

关键词： Face recognition

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：