检索结果-内蒙古大学图书馆

Instance-Consistent Fair Face Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第7期47卷 5319-5335页

作者： Yong Li Yufei Sun Zhen Cui Pengcheng Shen Shiguang Shan School of Computer Science and Engineering Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Nanjing China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Artificial Intelligence Beijing Normal University Beijing China Momenta Suzhou China State Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

The fairness of face recognition (FR) is a challenging issue to numerous FR algorithms in the modern pluralistic and egalitarian society. In this work, we propose an instance-consistent fair face recognition (IC-FFR) method by fulfilling complete instance fairness on false positive rate (FPR) and true positive rate (TPR). In view of the misalignment of testing and training metrics, not yet considered by the current fair FR algorithms, in theory, we inspect the correlation between the testing metrics (FPR and TPR) and the label classification loss, and we derive a high-probability consistency of unfairness penalties from FPR and TPR to the softmax loss. According to the theoretical analysis, we further develop an instance-consistent fairness solution by introducing customized instance margins, which well preserve consistent FPR and TPR of all instances during the label classification in training. To encourage more fine-grained fairness evaluation, we contribute a dataset called national faces in the world (NFW) to measure the fairness of individuals and countries. Extensive experiments on our NFW as well as the RFW and BFW benchmarks demonstrate the effectiveness and superiority of our method compared to those state-of-the-art fair FR methods.

关键词： Face recognition Training Measurement Annotations Accuracy Benchmark testing Electronic mail Sun Standards Loss measurement

来源：评论

学校读者我要写书评

暂无评论

Boosting LLMS with Ontology-Aware Prompt for Ner Data Augmentation

Boosting LLMS with Ontology-Aware Prompt for Ner Data Augmen...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zhizhao Luo Youchen Wang Wenjun Ke Rui Qi Yikai Guo Peng Wang Beijing Institute of Computer Technology and Application Beijing China School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University) Ministry of Education Nanjing China China Life Property & Casualty Insurance Company Limited Changsha China

Named Entity Recognition (NER) data augmentation (DA) aims to improve the performance and generalization capabilities of NER models by generating scalable training data. The key challenge lies in ensuring the generated samples maintain contextual diversity while preserving label consistency. However, existing dominant methods fail to simultaneously satisfy both criteria. Inspired by the extensive generative capabilities of large language models (LLMs), we propose ANGEL, a frAmework integrating the oNtoloGy structure and instructivE prompting within LLMs. Specifically, the hierarchical ontology structure guides prompt ranking, while instructive prompting enhances LLMs’ mastery of domain knowledge, empowering synthetic sample generation and annotation. Experiments show ANGEL surpasses state-of-the-art (SOTA) baselines, conferring absolute F1 increases of 2.86% and 0.93% on two benchmark datasets, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fast and Continual Knowledge Graph Embedding via Incremental LoRA

arXiv

引用

arXiv 2024年

作者： Liu, Jiajun Ke, Wenjun Wang, Peng Wang, Jiahao Gao, Jinhua Shang, Ziyu Li, Guozheng Xu, Zijie Ji, Ke Li, Yining School of Computer Science and Engineering Southeast University China Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Ministry of Education China Institute of Computing Technology Chinese Academy of Sciences China College of Software Engineering Southeast University China

Continual Knowledge Graph Embedding (CKGE) aims to efficiently learn new knowledge and simultaneously preserve old knowledge. Dominant approaches primarily focus on alleviating catastrophic forgetting of old knowledge but neglect efficient learning for the emergence of new knowledge. However, in real-world scenarios, knowledge graphs (KGs) are continuously growing, which brings a significant challenge to fine-tuning KGE models efficiently. To address this issue, we propose a fast CKGE framework (FastKGE), incorporating an incremental low-rank adapter (IncLoRA) mechanism to efficiently acquire new knowledge while preserving old knowledge. Specifically, to mitigate catastrophic forgetting, FastKGE isolates and allocates new knowledge to specific layers based on the fine-grained influence between old and new KGs. Subsequently, to accelerate fine-tuning, FastKGE devises an efficient IncLoRA mechanism, which embeds the specific layers into incremental low-rank adapters with fewer training parameters. Moreover, IncLoRA introduces adaptive rank allocation, which makes the LoRA aware of the importance of entities and adjusts its rank scale adaptively. We conduct experiments on four public datasets and two new datasets with a larger initial scale. Experimental results demonstrate that FastKGE can reduce training time by 34%-49% while still achieving competitive link prediction performance against state-of-the-art models on four public datasets (average MRR score of 21.0% vs. 21.1%). Meanwhile, on two newly constructed datasets, FastKGE saves 51%-68% training time and improves link prediction performance by 1.5%. Copyright © 2024, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Clinical Insight-Augmented Multi-View Learning for Alzheimer’s Detection in Retinal OCTA Images

Clinical Insight-Augmented Multi-View Learning for Alzheimer...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yuandi Zhang Jinkui Hao Botian Zheng Yonghuai Liu Yanda Meng Jiong Zhang Yang Chen Chunfeng Yang Yitian Zhao School of Computer Science and Engineering Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University)-Ministry of EducationSoutheast University Nanjing China Laboratory of Advanced Theranostic Materials and Technology Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Ningbo China Department of Computer Science Edge Hill University Ormskirk UK Department of Computer Science University of Exeter Exeter UK

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Alzheimer’s disease (AD) poses a significant global challenge, with a notable absence of accessible and cost-effective diagnostic tools for widespread AD detection. The retina, mirroring the brain in anatomy and physiology, has emerged as a potential avenue for rapid AD identification through retinal imaging. The current retinal image-based AD detection methods usually focus primarily on the macular area, but ignore the potential value that the optic disc region may have for the detection task. In this study, we leverage both macular- and disc-centered OCTA images and propose a multi-region fusion framework for AD detection. Based on clinical evidence, we integrate handcrafted features into the framework to improve model performance and interpretability. Specifically, vascular morphological parameters extracted from the macular and disc regions are used as input to a revalued KNN model to improve predictive capabilities. Furthermore, recognizing the significance of extracting and utilizing complementary information from the macular and optic disc regions, we propose an uncertainty-guided strategy based on Dempster-Shefer Theory (DST) to fuse knowledge from different regions. This approach considers each region’s forecast quality and significantly improves the effectiveness and robustness of the model. Through comparative analysis with existing methods, we have demonstrated that our method outperforms the state-of-the-art ones and provides more valuable pathological evidence for the association between retinal vascular changes and AD.

关键词： Accuracy Uncertainty Manuals Predictive models Feature extraction Retina Optical imaging Robustness Physiology Alzheimer's disease

来源：评论

学校读者我要写书评

暂无评论

Attribute-Aware Deep Hashing with Self-Consistency for Large-Scale Fine-Grained Image Retrieval

arXiv

引用

arXiv 2023年

作者： Wei, Xiu-Shen Shen, Yang Sun, Xuhao Wang, Peng Peng, Yuxin School of Computer Science and Engineering Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University China School of Computer Science and Engineering Nanjing University of Science and Technology China School of Computer Science and Engineering University of Electronic Science and Technology of China China Wangxuan Institute of Computer Technology National Key Laboratory for Multimedia Information Processing Peking University China

Our work focuses on tackling large-scale fine-grained image retrieval as ranking the images depicting the concept of interests (i.e., the same sub-category labels) highest based on the fine-grained details in the query. It is desirable to alleviate the challenges of both fine-grained nature of small inter-class variations with large intra-class variations and explosive growth of fine-grained data for such a practical task. In this paper, we propose attribute-aware hashing networks with self-consistency for generating attribute-aware hash codes to not only make the retrieval process efficient, but also establish explicit correspondences between hash codes and visual attributes. Specifically, based on the captured visual representations by attention, we develop an encoder-decoder structure network of a reconstruction task to unsupervisedly distill high-level attribute-specific vectors from the appearance-specific visual representations without attribute annotations. Our models are also equipped with a feature decorrelation constraint upon these attribute vectors to strengthen their representative abilities. Then, driven by preserving original entities' similarity, the required hash codes can be generated from these attribute-specific vectors and thus become attribute-aware. Furthermore, to combat simplicity bias in deep hashing, we consider the model design from the perspective of the self-consistency principle and propose to further enhance models' self-consistency by equipping an additional image reconstruction path. Comprehensive quantitative experiments under diverse empirical settings on six fine-grained retrieval datasets and two generic retrieval datasets show the superiority of our models over competing methods. Moreover, qualitative results demonstrate that not only the obtained hash codes can strongly correspond to certain kinds of crucial properties of fine-grained objects, but also our self-consistency designs can effectively overcome simplicity bias in fi

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

GDP-Net: Global Dependency-Enhanced Dual-Domain Parallel Network for Ring Artifact Removal

引用

IEEE Transactions on Medical Imaging 2025年第6期44卷 2718-2731页

作者： Yikun Zhang Guannan Liu Yang Liu Shipeng Xie Jiabing Gu Zujian Huang Xu Ji Tianling Lyu Yan Xi Shouping Zhu Jian Yang Yang Chen Laboratory of Image Science and Technology School of Computer Science and Engineering and the Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Ministry of Education Southeast University Nanjing China School of Communications and Information Engineering Nanjing University of Posts and Telecommunications Nanjing China The Affiliated Hospital of Qingdao University Qingdao China School of Life Science and Technology Xidian University Xi’an China Zhejiang Laboratory Hangzhou China Academy for Advanced Interdisciplinary Science and Technology Zhejiang University of Technology Hangzhou China Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Ministry of Education Southeast University Nanjing China Shanghai First-Imaging Information Technology Company Ltd. Shanghai China School of Optics and Photonics Beijing Institute of Technology Beijing China

In Computed Tomography (CT) imaging, the ring artifacts caused by the inconsistent detector response can significantly degrade the reconstructed images, having negative impacts on the subsequent applications. The new generation of CT systems based on photon-counting detectors are affected by ring artifacts more severely. The flexibility and variety of detector responses make it difficult to build a well-defined model to characterize the ring artifacts. In this context, this study proposes the global dependency-enhanced dual-domain parallel neural network for Ring Artifact Removal (RAR). First, based on the fact that the features of ring artifacts are different in Cartesian and Polar coordinates, the parallel architecture is adopted to construct the deep neural network so that it can extract and exploit the latent features from different domains to improve the performance of ring artifact removal. Besides, the ring artifacts are globally relevant whether in Cartesian or Polar coordinate systems, but convolutional neural networks show inherent shortcomings in modeling long-range dependency. To tackle this problem, this study introduces the novel Mamba mechanism to achieve a global receptive field without incurring high computational complexity. It enables effective capture of the long-range dependency, thereby enhancing the model performance in image restoration and artifact reduction. The experiments on the simulated data validate the effectiveness of the dual-domain parallel neural network and the Mamba mechanism, and the results on two unseen real datasets demonstrate the promising performance of the proposed RAR algorithm in eliminating ring artifacts and recovering image details.

关键词： Detectors Computed tomography Filtering Electronic mail Image reconstruction Feature extraction Computational modeling Calibration X-ray imaging Photonics

来源：评论

学校读者我要写书评

暂无评论

SETA: Semantic-Aware Token Augmentation for Domain Generalization

arXiv

引用

arXiv 2024年

作者： Guo, Jintao Qi, Lei Shi, Yinghuan Gao, Yang The National Key Laboratory for Novel Software Technology The National Institute of Healthcare Data Science Nanjing University Nanjing210023 China The School of Computer Science and Engineering Southeast University Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Ministry of Education Nanjing211189 China

Domain generalization (DG) aims to enhance the model robustness against domain shifts without accessing target domains. A prevalent category of methods for DG is data augmentation, which focuses on generating virtual samples to simulate domain shifts. However, existing augmentation techniques in DG are mainly tailored for convolutional neural networks (CNNs), with limited exploration in token-based architectures, i.e., vision transformer (ViT) and multi-layer perceptrons (MLP) models. In this paper, we study the impact of prior CNN-based augmentation methods on token-based models, revealing their performance is suboptimal due to the lack of incentivizing the model to learn holistic shape information. To tackle the issue, we propose the Semantic-aware Edge-guided Token Augmentation (SETA) method. SETA transforms token features by perturbing local edge cues while preserving global shape features, thereby enhancing the model learning of shape information. To further enhance the generalization ability of the model, we introduce two stylized variants of our method combined with two state-of-the-art (SOTA) style augmentation methods in DG. We provide a theoretical insight into our method, demonstrating its effectiveness in reducing the generalization risk bound. Comprehensive experiments on five benchmarks prove that our method achieves SOTA performances across various ViT and MLP architectures. Our code is available at https://***/lingeringlight/SETA. Copyright © 2024, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Incomplete Cross-Modal Hashing Retrieval

SSRN

引用

SSRN 2024年

作者： Peng, Shouyong Yao, Tao Li, Ying Wang, Gang Wang, Lili Yan, Zhiming Information and Electrical Engineering Ludong University Yantai China School of Computer and Electronic Information The School of Artificial Intelligence Nanjing Normal University Nanjing China Yantai Research Institute of New Generation Information Technology Southwest Jiaotong University Yantai China Ludong University China

Benefiting from fast retrieval speed and low storage costs, cross-modal hashing retrieval has become a widely-used approximate nearest-neighbor technique in large-scale data retrieval. Most existing cross-modal hashing methods assume that the cross-modal data points are complete. However, cross-modal data completeness is difficult to be satisfied in the real world, because of the indefinite factors in data collecting. Moreover, due to the expensive cost of annotating all data points in large-scale applications, there is a growing interest in unsupervised hashing retrieval that can learn the correlations of cross-modal data without ground-truth. Therefore, how to perform unsupervised hashing retrieval on incomplete cross-modal data becomes a problem worthy of study. In this paper, we propose a Self-supervised Incomplete Cross-modal Hashing retrieval (SICH) method, which integrates data recovery and hashing encoding into a unified framework. Specifically, we first design a self-supervised semantic module to effectively mine the semantic information among pseudo-labels, and then a hash code dictionary is constructed to guide the hashing function learning with an asymmetric guidance mechanism. Besides, to fully take advantage of the incomplete data points in cross-modal learning, we introduce a data recovery network aiming at recovering missing data by minimizing conditional entropy and maximizing mutual information between different modalities. Extensive experiments on two benchmark datasets verify that our method consistently outperforms state-of-the-art cross-modal hashing methods. © 2024, The Authors. All rights reserved.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Towards Better Performance in Incomplete LDL: Addressing Data Imbalance

arXiv

引用

arXiv 2024年

作者： Kou, Zhiqiang Xuan, Haoyuan Wang, Jing Jia, Yuheng Geng, Xin School of Computer Science and Engineering Southeast University Nanjing211189 China The Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Ministry of Education China The School of Computing & Information Sciences Caritas Institute of Higher Education Hong Kong

Label Distribution Learning (LDL) is a novel machine learning paradigm that addresses the problem of label ambiguity and has found widespread applications. Obtaining complete label distributions in real-world scenarios is challenging, which has led to the emergence of Incomplete Label Distribution Learning (InLDL). However, the existing InLDL methods overlook a crucial aspect of LDL data: the inherent imbalance in label distributions. To address this limitation, we propose Incomplete and Imbalance Label Distribution Learning (I2LDL), a framework that simultaneously handles incomplete labels and imbalanced label distributions. Our method decomposes the label distribution matrix into a low-rank component for frequent labels and a sparse component for rare labels, effectively capturing the structure of both head and tail labels. We optimize the model using the Alternating Direction Method of Multipliers (ADMM) and derive generalization error bounds via Rademacher complexity, providing strong theoretical guarantees. Extensive experiments on 15 real-world datasets demonstrate the effectiveness and robustness of our proposed framework compared to existing InLDL methods. © 2024, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Predictive intelligence and adaptive control strategies for ensuring safety in Island microgrids during load and power disturbances

引用

computers and Electrical Engineering 2024年 120卷

作者： Zhang, Jiyang Zhang, Meng Yang, Jie Zheng, Xiu School of Electrical Engineering and Automation Henan Institute of Technology Henan Xinxiang453003 China Henan Engineering Research Center of key Equipment for New Energy Power Generation Henan Xinxiang453003 China Henan Institute of Animal Husbandry Economics School of Energy and Intelligence Engineering Henan Zhengzhou450000 China Department of Computer Engineering Dongseo University Busan47011 Korea Republic of

Combined Cycle Power Plants offer an efficient and environmentally friendly means of electricity generation, albeit with challenges in accurately predicting power output. This study proposes a hybrid model to forecast the total electrical power load in these plants by leveraging key input variables. Five machine learning algorithms, including Categorical Boosting, Histogram-based Gradient Boosting Regression, Extreme Gradient Boosting Regression, Light Gradient Boosting Machine, and Support Vector Regression, were employed, with their predictions optimized using the Hunger Games Search algorithm. This integration resulted in five hybrid models, with the combination of Hunger Games Search and Categorical Boosting emerging as the most effective, demonstrating superior performance in test datasets with an R2 value of 0.9735 and a mean absolute error of 2.05525. The Hunger Games Search algorithm enhanced prediction accuracy by fine-tuning core algorithm parameters. Comprehensive case analysis and metric evaluation underscored the efficacy of the proposed model for hourly power load forecasting in Combined Cycle Power Plants, although the hybrid model combining Hunger Games Search and Support Vector Regression exhibited comparatively poorer performance in test datasets with R2 of 0.9551 and a mean absolute error of 2.71211. The recommendation to integrate Categorical Boosting with the Hunger Games Search algorithm stands as a robust strategy for enhancing power load prediction in these power plants, promising greater operational efficiency and reliability in electricity generation. © 2024 Elsevier Ltd

关键词： Hybrid power

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：