检索结果-内蒙古大学图书馆

AdaAugment: A Tuning-Free and Adaptive Approach to Enhance Data Augmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Suorong Li, Peijia Xiong, Xi Shen, Furao Zhao, Jian State Key Laboratory for Novel Software Technology Nanjing University China Department of Computer Science and Technology Nanjing University China School of Artificial Intelligence Nanjing University China School of Electronic Science and Engineering Nanjing University China

Data augmentation (DA) is widely employed to improve the generalization performance of deep models. However, most existing DA methods use augmentation operations with random magnitudes throughout training. While this fosters diversity, it can also inevitably introduce uncontrolled variability in augmented data, which may cause misalignment with the evolving training status of the target models. Both theoretical and empirical findings suggest that this misalignment increases the risks of underfitting and overfitting. To address these limitations, we propose AdaAugment, an innovative and tuning-free Adaptive Augmentation method that utilizes reinforcement learning to dynamically adjust augmentation magnitudes for individual training samples based on real-time feedback from the target network. Specifically, AdaAugment features a dual-model architecture consisting of a policy network and a target network, which are jointly optimized to effectively adapt augmentation magnitudes. The policy network optimizes the variability within the augmented data, while the target network utilizes the adaptively augmented samples for training. Extensive experiments across benchmark datasets and deep architectures demonstrate that AdaAugment consistently outperforms other state-of-the-art DA methods in effectiveness while maintaining remarkable efficiency. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

Uncertainty Quantification in Machine Learning Based Segmentation: A Post-Hoc Approach for Left Ventricle Volume Estimation in MRI

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Terhag, Felix Knechtges, Philipp Basermann, Achim Tempone, Raúl Institute for Software Technology Cologne Germany RWTH Aachen University Aachen Germany Computer Electrical and Mathematical Sciences and Engineering Division KAUST Thuwal Saudi Arabia

Recent studies have confirmed cardiovascular diseases remain responsible for highest death toll amongst non-communicable diseases. Accurate left ventricular (LV) volume estimation is critical for valid diagnosis and management of various cardiovascular conditions, but poses significant challenge due to inherent uncertainties associated with segmentation algorithms in magnetic resonance imaging (MRI). Recent machine learning advancements, particularly U-Net-like convolutional networks, have facilitated automated segmentation for medical images, but struggles under certain pathologies and/or different scanner vendors and imaging protocols. This study proposes a novel methodology for post-hoc uncertainty estimation in LV volume prediction using Itô stochastic differential equations (SDEs) to model path-wise behavior for the prediction error. The model describes the area of the left ventricle along the heart’s long axis. The method is agnostic to the underlying segmentation algorithm, facilitating its use with various existing and future segmentation technologies. The proposed approach provides a mechanism for quantifying uncertainty, enabling medical professionals to intervene for unreliable predictions. This is of utmost importance in critical applications such as medical diagnosis, where prediction accuracy and reliability can directly impact patient outcomes. The method is also robust to dataset changes, enabling application for medical centers with limited access to labeled data. Our findings highlight the proposed uncertainty estimation methodology’s potential to enhance automated segmentation robustness and generalizability, paving the way for more reliable and accurate LV volume estimation in clinical settings as well as opening new avenues for uncertainty quantification in biomedical image segmentation, providing promising directions for future *** Codes 68T07, 62P10, 92C55, 68T05, 65C20, 62M45 Copyright © 2023, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

Nerftap: Enhancing Transferability of Adversarial Patches on Face Recognition Using Neural Radiance Fields

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Liu, Xiaoliang Shen, Fu-Rao Han, Feng Zhao, Jian Nie, Changhai State Key Laboratory for Novel Software Technology Nanjing University China Department of Computer Science and Technology Nanjing University China School of Artificial Intelligence Nanjing University China School of Electronic Science and Engineering Nanjing University China

Face recognition (FR) technology plays a crucial role in various applications, but its vulnerability to adversarial attacks poses significant security concerns. Existing research primarily focuses on transferability to different FR models, overlooking the direct transferability to victim's face images, which is a practical threat in real-world scenarios. In this study, we propose a novel adversarial attack method that considers both the transferability to the FR model and the victim's face image, called NerfTAP. Leveraging Neural Radiance Fields (NeRF)-based 3D Generative Adversarial Network (GAN), we generate new view face images for the source and target subjects to enhance transferability of adversarial patches. We introduce a style consistency loss to ensure the visual similarity between the adversarial UV map and the target UV map under a 0-1 mask, enhancing the effectiveness and naturalness of the generated adversarial face images. Extensive experiments and evaluations on various FR models demonstrate the superiority of our approach over existing attack techniques. Our work provides valuable insights for enhancing the robustness of FR systems in practical adversarial settings. © 2024, The Authors. All rights reserved.

关键词： Face recognition

Edge computing service deployment and task offloading based on multi-task high-dimensional multi-objective optimization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Guo, Yanheng Zhang, Yan Wu, Linjie Li, Mengxia Cai, Xingjuan Chen, Jinjun Shanxi Key Laboratory of Big Data Analysis and Parallel Computing Taiyuan University of Science and Technology Shanxi Taiyuan030024 China State Key Laboratory for Novel Software Technology Nanjing University China Department of Computer Science and Software Engineering Swinburne University of Technology Melbourne Australia

The Mobile Edge Computing (MEC) system located close to the client allows mobile smart devices to offload their computations onto edge servers, enabling them to benefit from low-latency computing services. Both cloud service providers and users seek more comprehensive solutions, necessitating judicious decisions in service deployment and task offloading while balancing multiple objectives. This study investigates service deployment and task offloading challenges in a multi-user environment, framing them as a multi-task high-dimensional multi-objective optimization (MT-HD-MOO) problem within an edge environment. To ensure stable service provisioning, beyond considering latency, energy consumption, and cost as deployment objectives, network reliability is also incorporated. Furthermore, to promote equitable usage of edge servers, load balancing is introduced as a fourth task offloading objective, in addition to latency, energy consumption, and cost. Additionally, this paper designs a MT-HD-MOO algorithm based on a multi-selection strategy to address this model and its solution. By employing diverse selection strategies, an environment selection strategy pool is established to enhance population diversity within the high-dimensional objective space. Ultimately, the algorithm’s effectiveness is verified through simulation experiments. © 2023, CC BY-NC-ND.

关键词： Multiobjective optimization

TSEML: A task-specific embedding-based method for few-shot classification of cancer molecular subtypes

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Su, Ran Shi, Rui Cui, Hui Xuan, Ping Fang, Chengyan Feng, Xikang Jin, Qiangguo School of Computer Software College of Intelligence and Computing Tianjin University Tianjin China School of Software Northwestern Polytechnical University Shaanxi China Department of Computer Science and Information Technology La Trobe University Melbourne Australia Department of Computer Science School of Engineering Shantou University Guangdong China Yangtze River Delta Research Institute of Northwestern Polytechnical University Taicang China

Molecular subtyping of cancer is recognized as a critical and challenging upstream task for personalized therapy. Existing deep learning methods have achieved significant performance in this domain when abundant data samples are available. However, the acquisition of densely labeled samples for cancer molecular subtypes remains a significant challenge for conventional data-intensive deep learning approaches. In this work, we focus on the few-shot molecular subtype prediction problem in heterogeneous and small cancer datasets, aiming to enhance precise diagnosis and personalized treatment. We first construct a new few-shot dataset for cancer molecular subtype classification and auxiliary cancer classification, named TCGA Few-Shot, from existing publicly available datasets. To effectively leverage the relevant knowledge from both tasks, we introduce a task-specific embedding-based meta-learning framework (TSEML). TSEML leverages the synergistic strengths of a model-agnostic meta-learning (MAML) approach and a prototypical network (ProtoNet) to capture diverse and fine-grained features. Comparative experiments conducted on the TCGA Few-Shot dataset demonstrate that our TSEML framework achieves superior performance in addressing the problem of few-shot molecular subtype classification. Copyright © 2024, The Authors. All rights reserved.

关键词： Zero-shot learning

An Abstractive Summarization Technique with Variable Length Keywords as per Document Diversity

学校读者我要写书评

暂无评论

computers, Materials & Continua 2021年第3期66卷 2409-2423页

作者： Muhammad Yahya Saeed Muhammad Awais Muhammad Younas Muhammad Arif Shah Atif Khan M.Irfan Uddin Marwan Mahmoud Department of Software Engineering Government College UniversityFaisalabadFaisalabad38000Pakistan Department of IT and Computer Science Pak-Austria Fachhochschule Institute of Applied Sciences and TechnologyHaripurPakistan Department of Computer Science Islamia College PeshawarPeshawarPakistan Institute of Computing Kohat University of Science and TechnologyKohatPakistan Faculty of Applied Studies King Abdulaziz UniversityJeddahSaudi Arabia

Text Summarization is an essential area in text mining,which has procedures for text *** natural language processing,text summarization maps the documents to a representative set of descriptive ***,the objective of text extraction is to attain reduced expressive contents from the text *** summarization has two main areas such as abstractive,and extractive *** text summarization has further two approaches,in which the first approach applies the sentence score algorithm,and the second approach follows the word embedding *** such text extractions have limitations in providing the basic theme of the underlying *** this paper,we have employed text summarization by TF-IDF with PageRank keywords,sentence score algorithm,and Word2Vec word *** study compared these forms of the text summarizations with the actual text,by calculating cosine ***,TF-IDF based PageRank keywords are extracted from the other two extractive *** intersection over these three types of TD-IDF keywords to generate the more representative set of keywords for each text document is *** technique generates variable-length keywords as per document diversity instead of selecting fixedlength keywords for each *** form of abstractive summarization improves metadata similarity to the original text compared to all other forms of summarized *** also solves the issue of deciding the number of representative keywords for a specific text *** evaluate the technique,the study used a sample of more than eighteen hundred text *** abstractive summarization follows the principles of deep learning to create uniform similarity of extracted words with actual text and all other forms of text *** proposed technique provides a stable measure of similarity as compared to existing forms of text summarization.

关键词： Metadata page rank sentence score word2vec cosine similarity This

Day-ahead PV Output Power Forecasting Utilizing Boosting Recursive LightGBM-LSTM Framework

学校读者我要写书评

暂无评论

Day-ahead PV Output Power Forecasting Utilizing Boosting Rec...

IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT Europe)

作者： Hossein Nourollahi Hokmabad Oleksandr Husev Dmitri Vinnikov Juri Belikov Eduard Petlenkov Department of Electrical Power Engineering and Mechatronics Tallinn University of Technology Tallinn Estonia Department of Software Science Tallinn University of Technology Tallinn Estonia Department of Computer Systems Tallinn University of Technology Tallinn Estonia

Recently, global photovoltaic (PV) system installations have surged. Precise forecasting is vital for their grid integration and carbon emission cuts. However, due to fluctuating solar radiation, predicting PV output is difficult. Machine learning models, notably Long Short-Term Memory (LSTM) networks, offer a solution. This study presents a novel framework using a boosted recursive Light Gradient Boosting Machine (LightGBM)-LSTM network to forecast daily PV output at hourly intervals. Conducted in Northern Europe—a region with significant solar radiation variability—the models trained on meteorological and historical data showed a 12% improvement in RMSE, a 13% reduction in MAPE, and a 5% increase in the R 2 score compared to standalone LSTM models.

关键词：

Detecting Deepfakes: using CNN to Identify Manipulated Visual Media

学校读者我要写书评

暂无评论

Detecting Deepfakes: using CNN to Identify Manipulated Visua...

International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)

作者： N. Sunanda K. Shailaja Jampani Satish Babu K Vamsi Krishna N. LakshmanPratap Ravi Kanth Motupalli Department of CSE-(CyS DS) and AI&DS VNR Vignana Jyothi Institute of Engineering & Technology Hyderabad Department of CSE Vasavi College of Engineering & Technology Hyderabad Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Guntur Prowess Software Services Hyderabad Department of ECE Mallareddy Engineering College Hyderabad Department of CSE VNR Vignana Jyothi Institute of Engineering & Technology Hyderabad

ISBN: (数字)9798350376425

ISBN: (纸本)9798350376432

Deepfake detection is a rapidly evolving field with significant implications for the integrity of visual media. This review explores techniques, challenges, and future directions in deepfake detection. Traditional image forensics techniques, deep learning models, and multi-modal fusion approaches are employed to differentiate real content from deepfakes. Addressing the challenges of evolving deepfake algorithms and the need for real-time detection, future research should focus on novel architectures, training strategies, temporal and contextual information, and ethical considerations. By advancing deepfake detection methods, researchers can contribute to combating the proliferation of synthetic content and preserving the authenticity of visual media in the digital age.

关键词： Training Deepfakes Visualization Machine learning algorithms Reviews Information age Robustness Real-time systems Convolutional neural networks Optical flow

EmoBench-M: Benchmarking Emotional Intelligence for Multimodal Large Language Models

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Hu, He Zhou, Yucheng You, Lianzhong Xu, Hongbo Wang, Qianning Lian, Zheng Yu, Fei Richard Ma, Fei Cui, Laizhong College of Computer Science and Software Engineering Shenzhen University China China SKL-IOTSC CIS University of Macau China Auckland University of Technology New Zealand Institute of Automation Chinese Academy of Sciences China

With the integration of Multimodal large language models (MLLMs) into robotic systems and various AI applications, embedding emotional intelligence (EI) capabilities into these models is essential for enabling robots to effectively address human emotional needs and interact seamlessly in real-world scenarios. Existing static, text-based, or text-image benchmarks overlook the multimodal complexities of real-world interactions and fail to capture the dynamic, multimodal nature of emotional expressions, making them inadequate for evaluating MLLMs’ EI. Based on established psychological theories of EI, we build EmoBench-M, a novel benchmark designed to evaluate the EI capability of MLLMs across 13 valuation scenarios from three key dimensions: foundational emotion recognition, conversational emotion understanding, and socially complex emotion analysis. Evaluations of both open-source and closed-source MLLMs on EmoBench-M reveal a significant performance gap between them and humans, highlighting the need to further advance their EI capabilities. All benchmark resources, including code and datasets, are publicly available at https://***/. Copyright © 2025, The Authors. All rights reserved.

关键词： Emotional intelligence