检索结果-内蒙古大学图书馆

Correction to: Consistent Prompt Tuning for Generalized Category Discovery (International Journal of Computer Vision, (2025), 10.1007/s11263-024-02343-w)

引用

International Journal of Computer Vision 2025年 1-10页

作者： Yang, Muli Yin, Jie Gu, Yanan Deng, Cheng Zhang, Hanwang Zhu, Hongyuan Singapore Singapore School of Electronic Engineering Xidian University Xi’an China Norinco Group Testing and Research Institute Xi’an China College of Computing and Data Science Nanyang Technological University Singapore Singapore

The original publication of this article was published with several errors and has been corrected as follows. In the Section 4.3.1, the hyperlink for the Section 5 citation was missing and has been included. In Table 6, the significance ‘Reimplemented using CLIP’s image encoder’ was incorrectly provided for the method ‘CPT (Ours) and has been removed. In Table 12, the method name was incorrectly listed as ‘CLIP-GC’ but should read as ‘CLIP-GCD’. Additionally, the significance ‘Reimplemented using (Open/Meta) CLIP’s image encoder’ was missing for the method ‘CLIP-GCD’ and has been included. In Table 15, the incorrect significance ‘Reimplemented using CLIP’s image encoder’ was provided for the methods GCD (2022a), SimGCD (2023) and GPC (2023). This should be removed and the correct significance ‘Training with estimated category number’ has been included. In Table 22, the species "andrias acropora acuminata (staghorn coral)" was missing and has been included before the species "andrias davidianus (chinese giant salamander)." For completeness and transparency, the old incorrect and the corrected versions of Tables are displayed below. The original article has been corrected. Incorrect Table 6: GCD accuracy (%) in the customized setting on NICO dataset dataset → NICO-10 NICO-33 NICO-100 Method ↓ All Old New All Old New All Old New GCD (2022a) 95.1 97.3 94.0 38.6 58.4 25.1 48.0 67.0 39.1 PromptCAL (2023b) 89.6 80.9 93.6 30.5 42.4 22.5 45.3 53.4 41.5 SimGCD (2023) 97.3 97.0 97.4 45.9 67.7 46.3 65.1 37.4 PIM (2023) 96.4 97.2 96.0 42.2 67.6 24.9 49.5 67.5 41.0 GCD† 98.0 39.3 65.0 21.8 51.6 54.5 PromptCAL† 97.5 97.1 29.2 41.8 20.6 48.9 64.4 41.7 SimGCD† 97.5 46.6 29.1 69.4 44.6 PIM† 97.5 97.0 71.8 50.0 39.2 CPT (Ours)† 98.5 Bold value indicates the best results and underlined value indicates the second best results †Reimplemented using CLIP’s image encoder Corrected Table 6: GCD accuracy (%) in the customized setting on NICO dataset dataset → NICO-10 NICO-33 NICO-100 Method ↓

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Harmless Rawlsian Fairness Regardless of Demographic Prior 38

Towards Harmless Rawlsian Fairness Regardless of Demographic...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wang, Xuanqian Li, Jing Tsang, Ivor W. Ong, Yew-Soon School of Computer Science and Engineering Beihang University China Institute of High-Performance Computing Agency for Science Technology and Research Singapore Centre for Frontier AI Research Agency for Science Technology and Research Singapore College of Computing and Data Science Nanyang Technological University Singapore

Due to privacy and security concerns, recent advancements in group fairness advocate for model training regardless of demographic information. However, most methods still require prior knowledge of demographics. In this study, we explore the potential for achieving fairness without compromising its utility when no prior demographics are provided to the training set, namely harmless Rawlsian fairness. We ascertain that such a fairness requirement with no prior demographic information essential promotes training losses to exhibit a Dirac delta distribution. To this end, we propose a simple but effective method named VFair to minimize the variance of training losses inside the optimal set of empirical losses. This problem is then optimized by a tailored dynamic update approach that operates in both loss and gradient dimensions, directing the model towards relatively fairer solutions while preserving its intact utility. Our experimental findings indicate that regression tasks, which are relatively unexplored from literature, can achieve significant fairness improvement through VFair regardless of any prior, whereas classification tasks usually do not because of their quantized utility measurements. The implementation of our method is publicly available at https://***/wxqpxw/VFair. © 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

IGED:Towards Intelligent DDoS Detection Model Using Improved Generalized Entropy and DNN

引用

Computers, Materials & Continua 2024年第8期80卷 1851-1866页

作者： Yanhua Liu Yuting Han HuiChen Baokang Zhao XiaofengWang Ximeng Liu College of Computer and Data Science Fuzhou UniversityFuzhou350108China Engineering Research Center of Big Data Intelligence Ministry of EducationFuzhou350108China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou UniversityFuzhou350108China College of Computer National University of Defense TechnologyChangsha410073China

As the scale of the networks continually expands,the detection of distributed denial of service(DDoS)attacks has become increasingly *** propose an intelligent detection model named IGED by using improved generalized entropy and deep neural network(DNN).The initial detection is based on improved generalized entropy to filter out as much normal traffic as possible,thereby reducing data *** the fine detection is based on DNN to perform precise DDoS detection on the filtered suspicious traffic,enhancing the neural network’s generalization *** results show that the proposed method can efficiently distinguish normal traffic from DDoS *** with the benchmark methods,our method reaches 99.9%on low-rate DDoS(LDDoS),flooded DDoS and CICDDoS2019 datasets in terms of both accuracy and efficiency in identifying attack flows while reducing the time by 17%,31%and 8%.

关键词： DDoS real-time improved generalized entropy DNN

来源：评论

学校读者我要写书评

暂无评论

dataSET PRUNING: REDUCING TRAINING data BY EXAMINING GENERALIZATION INFLUENCE 11

DATASET PRUNING: REDUCING TRAINING DATA BY EXAMINING GENERAL...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Yang, Shuo Xie, Zeke Peng, Hanyu Xu, Min Sun, Mingming Li, Ping School of Electrical and Data Engineering University of Technology Sydney Australia Cognitive Computing Lab Baidu Research China

The great success of deep learning heavily relies on increasingly larger training data, which comes at a price of huge computational and infrastructural *** poses crucial questions that, do all training data contribute to model's performance? How much does each individual training sample or a sub-training-set affect the model's generalization, and how to construct the smallest subset from the entire training data as a proxy training set without significantly sacrificing the model's performance? To answer these, we propose dataset pruning, an optimization-based sample selection method that can (1) examine the influence of removing a particular set of training samples on model's generalization ability with theoretical guarantee, and (2) construct the smallest subset of training data that yields strictly constrained generalization *** empirically observed generalization gap of dataset pruning is substantially consistent with our theoretical ***, the proposed method prunes 40% training examples on the CIFAR-10 dataset, halves the convergence time with only 1.3% test accuracy decrease, which is superior to previous score-based sample selection methods. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Lung Cancer Classification with Ensemble Deep Learning Models 11

Enhancing Lung Cancer Classification with Ensemble Deep Lear...

引用

11th International Conference on Computer, Control, Informatics and its Applications, IC3INA 2024

作者： Waskita, A.A. Amda, Julfa Muhammad Sihono, Dwi Seno Kuncoro Research Center for Data and Information Sciences National Research and Innovation Agency Bandung Indonesia Department of Physics Universitas Indonesia Depok Indonesia Research Center for Computing National Research and Innovation Agency Cibinong Indonesia

ISBN: (纸本)9798331542313

This study creates ensemble models from several pretrained models to classify 3 classes of lung cancer, including benign, malignant, and normal. The pretrained models that we use are EfficientNetV2B0, ResNet50V2, and DenseNet121, which were trained separately and then integrated using the average ensemble technique to improve prediction accuracy. The model training process is carried out by utilizing transfer learning, where the basic layers of the previously trained model on the ImageNet dataset are frozen to maintain previously acquired knowledge. New fully connected layers are then added and trained to adapt the model to the specific classification task of lung cancer. In addition, the fine-tuning process is carried out by reopening some of the frozen layers to further refine the model’s performance on the lung cancer dataset that we use. The results of the study show that the developed ensemble models produces higher accuracy compared to individual models. With the ensemble models that have been built, it is hoped that it can be an effective tool in helping to classify lung cancer quickly, accurately, and can contribute to increasing the chances of patient recovery. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

MSSThreD: Multitask Social Media Sentiment Analysis with Sarcasm for Public Security Threat Detection 11

MSSThreD: Multitask Social Media Sentiment Analysis with Sar...

引用

11th International Conference on Information Technology, Computer and Electrical Engineering, ICITACEE 2024

作者： Suhaimin, Mohd Suhairi Md Hijazi, Mohd Hanafi Ahmad Moung, Ervin Gubin Politeknik Kota Bharu College Education Department of Polytechnic and Community Kelantan Kota Bharu Malaysia Universiti Malaysia Sabah Data Technology and Applications Research Group Creative Advanced Machine Intelligence Research Centre Faculty of Computing and Informatics Sabah Malaysia Universiti Malaysia Sabah Data Technology and Applications Research Group Faculty of Computing and Informatics Sabah Malaysia

ISBN: (纸本)9798350389289

Public security threat detection is critical for maintaining safety of citizens from possible natural or non-natural disasters. Social media, with its vast and diverse content, serves as a significant source for communication and information dissemination. Early detection of threats through social media analysis can greatly benefit in prevention before the event, or response and rescue during the event. However, the noisy textual with linguistic nature of social media content presents substantial challenges for sentiment analysis. Coupling with sarcasm can reverse the polarity of sentiments, complicating threat detection efforts. To address these challenges, we introduce an application framework for public security threat detection that embeds multitask learning, incorporating sentiment analysis and sarcasm detection. This application utilized preprocessing and feature engineering techniques based on Natural Language Processing to capture the nuance of sentiment and sarcasm, with deep learning network model of Bidirectional Long Short-Term Memory and Gated Recurrent Unit combination. The sentiment filtering and identifying threat-related keywords, producing monitoring reports that highlight threats earlier than traditional web news sources, as evidenced by our case study results. This application demonstrates the practical utility and impact of the framework in enhancing public security through timely threat detection. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Learning for Spatio-temporal and Relational data

Learning for Spatio-temporal and Relational Data

引用

2023 IEEE International Conference on Big data, Bigdata 2023

作者： Nam, Kihyuk Lee, Taewhi Kim, Sung-Soo Shin, Insik Smart Data Research Section Etri Daejeon Korea Republic of School of Computing Kaist Daejeon Korea Republic of

ISBN: (纸本)9798350324457

The vast amounts of spatio-temporal data generated by a variety of devices are best utilized in conjunction with relational, tabular data rather than being referenced separately. To enhance the efficiency of data analysis, learned models are frequently used to approximate query results by increasing responsiveness at the cost of some accuracy. Machine learning techniques exist for spatio-temporal data and tabular data separately, but it is not straightforward to represent the combined data in a unified learned model. This paper explores the challenge of learning from heterogeneous data, particularly trajectory and tabular data, and proposes approaches for representation learning using probabilistic circuits and deep neural networks. © 2023 IEEE.

关键词： Approximate Query Processing Big data Analysis Probabilistic Circuits SPNs Sum-Product Networks

来源：评论

学校读者我要写书评

暂无评论

LEMTL: Enhancing the pharmacokinetic predictions of multitask learning with existing pharmacokinetics

LEMTL: Enhancing the pharmacokinetic predictions of multitas...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Li, Ying Deng, Xiao Lv, Jingsong Chen, Hongyang Yang, Yao Zhejiang Lab Research Center for Space Computing System Zhejiang Province Hangzhou China Zhejiang Lab Research Center for Data Hub and Security Zhejiang Province Hangzhou China

ISBN: (纸本)9798350386226

Evaluation of pharmacokinetic properties such as absorption, distribution, metabolism, excretion, and toxicity is essential but costly and time-consuming in the research and development of new drug candidates. This challenge has driven many researchers to use multitask learning for in silico predictions. Given extra information such as SMILES (simplified molecular input line entry system) as input data, existing multitask learning methods can usually have a good performance in predicting pharmacokinetics, which are served as labels/tasks. However, most of these methods are based solely on additional information, overlooking potentially available pharmacokinetics, which can be utilized to further enhance the prediction of unavailable ones. To address this limitation, we propose Label Enhanced MultiTask Learning (LEMTL), a framework to improve the prediction accuracy of unknown pharmacokinetics of existing multitask learning methods by aggregating shared feature representations learned from additional information and from known pharmacokinetics. Experiments on synthetic and real datasets demonstrate significant improvements over the associated multitask learning approaches when incorporated within the LEMTL framework. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

RevMUX: data Multiplexing with Reversible Adapters for Efficient LLM Batch Inference

RevMUX: Data Multiplexing with Reversible Adapters for Effic...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Xu, Yige Guo, Xu Zeng, Zhiwei Miao, Chunyan Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly Singapore College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)9798891761643

Large language models (LLMs) have brought a great breakthrough to the natural language processing (NLP) community, while leading the challenge of handling concurrent customer queries due to their high throughput demands. data multiplexing addresses this by merging multiple inputs into a single composite input, allowing more efficient inference through a shared forward pass. However, as distinguishing individuals from a composite input is challenging, conventional methods typically require training the entire backbone, yet still suffer from performance degradation. In this paper, we introduce RevMUX, a parameter-efficient data multiplexing framework that incorporates a reversible design in the multiplexer, which can be reused by the demultiplexer to perform reverse operations and restore individual samples for classification. Extensive experiments on four datasets and three types of LLM backbones demonstrate the effectiveness of RevMUX for enhancing LLM inference efficiency while retaining a satisfactory classification performance. © 2024 Association for Computational Linguistics.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Effectiveness of Feedback Provision in Intelligent Tutoring Systems 9th

Analysis of the Effectiveness of Feedback Provision in Intel...

引用

9th International Conference on computing and Informatics, ICOCI 2023

作者： Jamaludin, Nur Hafiza Romli, Rohaida School of Computing Universiti Utara Malaysia UUM Sintok Kedah06010 Malaysia Data Management & Software Solution Research Laboratory School of Computing Universiti Utara Malaysia UUM Sintok Kedah06010 Malaysia

ISBN: (纸本)9789819995912

The effectiveness of feedback provision in an Intelligent Tutoring System (ITS) is a crucial aspect to be considered when developing a tutoring system. The system is proven beneficial if it can act like a one-to-one human tutor, which provides feedback based on student learning aptitude and performance. Many researchers have developed ITSs with the intention of assisting students in teaching programming concepts, algorithms, and writing computer programs. However, there have been very few studies that have focused on reviewing these works. The studies are merely concerned with reviewing the characteristic, application, evaluation, and supplementary features of ITSs across different educational fields from 2007 until 2017. As a result, a comparative evaluation was conducted with the goal of analyzing the feedback provided by existing works in ITSs as well as the techniques used to develop a student model. The results of this study have indicated that Constraint-Based modeling, Model Tracing, Natural Language processing, and Deep Learning with delayed feedback are the most appropriate feedback for students learning to code. Bayesian Network is the most commonly used technique by researchers with immediate and delayed feedback to help students learn programming concepts and algorithms better. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Students

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：