检索结果-内蒙古大学图书馆

PG-LBO: Enhancing High-Dimensional Bayesian Optimization with Pseudo-Label and Gaussian Process Guidance

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chen, Taicai Duan, Yue Li, Dong Qi, Lei Shi, Yinghuan Gao, Yang National Key Laboratory for Novel Software Technology Nanjing University China Huawei Noah’s Ark Lab China School of Computer Science and Engineering Southeast University China

Variational Autoencoder based Bayesian Optimization (VAE-BO) has demonstrated its excellent performance in addressing high-dimensional structured optimization problems. However, current mainstream methods overlook the potential of utilizing a pool of unlabeled data to construct the latent space, while only concentrating on designing sophisticated models to leverage the labeled data. Despite their effective usage of labeled data, these methods often require extra network structures, additional procedure, resulting in computational inefficiency. To address this issue, we propose a novel method to effectively utilize unlabeled data with the guidance of labeled data. Specifically, we tailor the pseudo-labeling technique from semi-supervised learning to explicitly reveal the relative magnitudes of optimization objective values hidden within the unlabeled data. Based on this technique, we assign appropriate training weights to unlabeled data to enhance the construction of a discriminative latent space. Furthermore, we treat the VAE encoder and the Gaussian Process (GP) in Bayesian optimization as a unified deep kernel learning process, allowing the direct utilization of labeled data, which we term as Gaussian Process guidance. This directly and effectively integrates the goal of improving GP accuracy into the VAE training, thereby guiding the construction of the latent space. The extensive experiments demonstrate that our proposed method outperforms existing VAE-BO algorithms in various optimization scenarios. Our code will be published at https://***/TaicaiChen/PG-LBO. Copyright © 2023, The Authors. All rights reserved.

关键词： Gaussian distribution

FedABC: Targeting Fair Competition in Personalized Federated Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Dui Shen, Li Luo, Yong Hu, Han Su, Kehua Wen, Yonggang Tao, Dacheng National Engineering Research Center for Multimedia Software School of Computer Science Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China Hubei Luojia Laboratory Wuhan China JD Explore Academy China School of Information and Electronics Beijing Institute of Technology China School of Computer Science and Engineering Nanyang Technological University Singapore

Federated learning aims to collaboratively train models without accessing their client’s local private data. The data may be Non-IID for different clients and thus resulting in poor performance. Recently, personalized federated learning (PFL) has achieved great success in handling Non-IID data by enforcing regularization in local optimization or improving the model aggregation scheme on the server. However, most of the PFL approaches do not take into account the unfair competition issue caused by the imbalanced data distribution and lack of positive samples for some classes in each client. To address this issue, we propose a novel and generic PFL framework termed Federated Averaging via Binary Classification, dubbed FedABC. In particular, we adopt the "one-vs-all" training strategy in each client to alleviate the unfair competition between classes by constructing a personalized binary classification problem for each class. This may aggravate the class imbalance challenge and thus a novel personalized binary classification loss that incorporates both the under-sampling and hard sample mining strategies is designed. Extensive experiments are conducted on two popular datasets under different settings, and the results demonstrate that our FedABC can significantly outperform the existing counterparts. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

Deep Learning-based Image Text Processing Research*

学校读者我要写书评

暂无评论

Deep Learning-based Image Text Processing Research*

IEEE International Conference on Big Data Security on Cloud (BigDataSecurity), High Performance and Smart Computing (HPSC) and Intelligent Data and Security (IDS)

作者： Huixuan Xiong Kai Jin Jingnian Liu Jiahong Cai Lijun Xiao School of Computer Science and Engineering Hunan University of Science and Technology Hunan Key Laboratory for Service Computing and Novel Software Technology Xiangtan China the College of Computer Science and Electronics Engineering Hunan University Changsha China Big Data Development and Research Center Guangzhou College of Technology and Business Guangzhou China

Deep learning is a powerful multi-layer architecture that has important applications in image processing and text classification. This paper first introduces the development of deep learning and two important algorithms of deep learning: convolutional neural networks and recurrent neural networks. The paper then introduces three applications of deep learning for image recognition, image detection, and image forensics, as well as three text classification methods based on convolutional neural networks, recurrent neural networks, and other text classification methods. Finally, the development trend of deep learning in the field of text and image processing and the difficulties to be further researched are summarised and prospected.

关键词： Deep learning Image forensics Recurrent neural networks Computational modeling Text categorization Feature extraction Data models

Enhancing road safety with DL vision: Do driver distraction alerts hold the key?

学校读者我要写书评

暂无评论

Neural Computing and Applications 2025年 1-21页

作者： Ali, Luqman Swavaf, Muhammad Alnajjar, Fady Zou, Zhao Mohan Ambali Parambil, Medha Mubin, Omar AlJassmi, Hamad Emirates Center for Mobility Research UAE University Abu Dhabi Al Ain United Arab Emirates Department of Civil and Environmental Engineering College of Engineering UAE University Abu Dhabi Al Ain United Arab Emirates Department of Computer Science and Software Engineering College of IT UAE University Abu Dhabi Al Ain United Arab Emirates School of Computer Data and Mathematical Sciences Western Sydney University SydneyNSW Australia

Driver distraction is a significant contributor to road accidents and traffic safety challenges. This study evaluates the performance of various YOLO models trained on a combination of custom and publicly available datasets, with their performance assessed using metrics such as mAP@50, precision, recall, F1-score, inference time, FPS, and model parameters. The aim is to determine the best trade-off between accuracy, speed, and computational efficiency, providing insights into the practical applicability of these models for distracted driving detection. Among the models, YOLOv8l achieves the highest accuracy with a mAP@50 of 0.921, precision of 0.911, recall of 0.895, and an F1-score of 0.899, making it suitable for scenarios prioritizing detection precision. YOLOv5m balances accuracy and efficiency, achieving a mAP@50 of 0.917 and an F1-score of 0.896, while maintaining moderate inference times. For real-time applications, YOLOv5n and YOLOv8n offer the fastest speeds, with inference times of 0.9 ms and FPS of 1111, at the cost of reduced accuracy. YOLOv8m provides a balance between performance and speed, achieving a mAP@50 of 0.915 and F1-score of 0.898, with an inference time of 3.4 ms and FPS of 294. A post-simulation survey reveals that participants find the visual warning system effective in mitigating driver distraction and enhancing perceived road safety. By integrating simulation data and user feedback, this study highlights the potential of advanced deep learning models like YOLO in improving driver assistance systems and promoting safer driving practices. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Highway accidents

A collaborative decomposition-based evolutionary algorithm integrating normal and penalty-based boundary intersection for many-objective optimization

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wu, Yu Wei, Jianle Ying, Weiqin Lan, Yanqi Cui, Zhen Wang, Zhenyu School of Computer Science and Cyber Engineering Guangzhou University Guangzhou510006 China School of Software Engineering South China University of Technology Guangzhou510006 China

Decomposition-based evolutionary algorithms have become fairly popular for many-objective optimization owing to their excellent selection pressure in recent years. However, the existing decomposition methods still are quite sensitive to the various shapes of frontiers of many-objective optimization problems (MaOPs). On the one hand, the cone decomposition methods such as the penalty-based boundary intersection (PBI) are incapable of acquiring uniform frontiers due to the radial spatial distribution of their reference lines for MaOPs with very convex frontiers. On the other hand, the parallel reference lines of the parallel decomposition methods including the normal boundary intersection (NBI) might result in poor diversity because of under-sampling near the boundaries for MaOPs with concave frontiers. In this paper, a collaborative decomposition method is first proposed to integrate the advantages of parallel decomposition and cone decomposition to overcome their respective disadvantages. This method inherits the NBI-style Tchebycheff function as a convergence measure to heighten the convergence and uniformity of distribution of the PBI method. Moreover, this method also adaptively tunes the extent of rotating an NBI reference line towards a PBI reference line for every subproblem to enhance the diversity of distribution of the NBI method. Furthermore, a collaborative decomposition-based evolutionary algorithm (CoDEA) is presented for many-objective optimization. A collaborative decomposition-based environmental selection mechanism is primarily designed in CoDEA to rank all the individuals associated with the same PBI reference line in the boundary layer and pick out the best ranks. The proposed algorithm is compared with several popular many-objective evolutionary algorithms on 85 benchmark test instances. The experimental results show that CoDEA achieves high competitiveness benefiting from the collaborative decomposition maintaining a good balance among the conve

关键词： Evolutionary algorithms

Adaptive Quantization based on Ensemble Distillation to Support FL enabled Edge Intelligence

学校读者我要写书评

暂无评论

Adaptive Quantization based on Ensemble Distillation to Supp...

GLOBECOM 2022 - 2022 IEEE Global Communications Conference

作者： Yi-Jing Liu Shuang Qin Gang Feng Dusit Niyato Yao Sun Jianhong Zhou National Key Laboratory of Science and Technology on Communications Yangtze Delta Region Institute (Huzhou) University of Electronic Science and Technology of China School of Computer Science and Engineering Nanyang Technological University James Watt School of Engineering University of Glasgow School of Computer and Software Engineering Xihua University

ISBN: (纸本)9781665435413

Federated learning (FL) has recently become one of the most acknowledged technologies in promoting the development of intelligent edge networks with the ever-increasing computing capability of user equipment (UE). In traditional FL paradigm, local models are usually required to be homogeneous for aggregation to achieve an accurate global model. Moreover, considerable communication cost and training time may be incurred in resource-constrained edge networks due to a large number of UEs participating in model transmission and the large size of transmitted models. Therefore, it is imperative to develop effective training schemes for heterogeneous FL models, while reducing communication cost as well as training time. In this paper, we propose an adaptive quantization scheme based on ensemble distillation (AQeD) for FL to facilitate personalized quantized model training over heterogeneous local models with different size, structure, and quantization level, etc. Specifically, we design an augmented loss function by jointly considering distillation loss function, quantization values and available wireless resources, where UEs train their local personalized machine learning models and send the quantized models to a server. Based on local quantized models, the server first performs global aggregation for cluster ensembles and then sends the aggregated model of the cluster back to the participating UEs. Numerical results show that our proposed AQeD scheme can significantly reduce communication cost as well as training time in comparison with some known state-of-the-art solutions.

关键词： Training Adaptation models Quantization (signal) Costs Federated learning Computational modeling Wireless networks

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zeng, Yu Zhang, Yang Liu, Jiachen Shen, Linlin Deng, Kaijun He, Weizhao Wang, Jinbao Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images. © 2024, CC BY.

关键词： Color image processing

TPE for JPEG images with Dynamic M-ary Decomposition and Adaptive Threshold Constraints

学校读者我要写书评

暂无评论

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Ma, Yakun Chai, Xiuli Long, Guoqiang Gan, Zhihua Zhang, Yushu Henan University School of Artificial Intelligence Henan Engineering Research Center for Industrial Internet of Things Zhengzhou450046 China Henan University School of Software Intelligent Data Processing Engineering Research Center of Henan Province Institute of Intelligent Network System Kaifeng475004 China Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing211106 China

Traditional JPEG image encryption that prioritizes solely confidentiality fails to account for the pressing usability requirements of cloud-based environments, thus boosting the boom in thumbnail-preserving encryption (TPE) to balance image privacy and usability. However, existing TPE schemes for JPEG images face numerous challenges, such as insufficient security, inability to achieve lossless decryption, and high file extension. To address these challenges, we propose a TPE scheme based on dynamic M-ary decomposition and adaptive threshold constraints (TPE-MDTC). First, the valid ranges of quantized DC coefficients for JPEG images are determined. Then, a sum-preserving encryption method for quantized DC coefficients with compliance threshold constraints is designed using the bit-plane permutation to preserve thumbnails with high accuracy. Next, the introduction of dynamic M-ary decomposition effectively changes bit statistical characteristics preserved by bit-plane permutation, enhancing the ciphertext security. Finally, a quantized AC encryption method with RV (Run/Value) pair global permutation is proposed, effectively modifying the unit block features, thereby significantly improving the security and attack resistance of encrypted images. Experimental results show that the proposed TPE-MDTC scheme can reconstruct the original JPEG images without loss, and the generated ciphertext images exhibit significant advantages over previous schemes regarding file extension and security. © 1991-2012 IEEE.

关键词： Ciphertext

DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization

学校读者我要写书评

暂无评论

DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fiel...

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Jiahe Li Jiawei Zhang Xiao Bai Jin Zheng Xin Ning Jun Zhou Lin Gu State Key Laboratory of Complex & Critical Software Environment School of Computer Science and Engineering Jiangxi Research Institute Beihang University Institute of Semiconductors Chinese Academy of Sciences School of Information and Communication Technology Griffith University RIKEN AIP The University of Tokyo

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Radiance fields have demonstrated impressive performance in synthesizing novel views from sparse input views, yet prevailing methods suffer from high training costs and slow inference speed. This paper introduces DNGaussian, a depth-regularized framework based on 3D Gaussian radiance fields, offering real-time and high-quality few-shot novel view synthesis at low costs. Our motivation stems from the highly efficient representation and surprising quality of the recent 3D Gaussian Splatting, despite it will encounter a geometry degradation when input views decrease. In the Gaussian radiance fields, we find this degradation in scene geometry primarily lined to the positioning of Gaussian primitives and can be mitigated by depth constraint. Consequently, we propose a Hard and Soft Depth Regularization to restore accurate scene geometry under coarse monocular depth supervision while maintaining a fine-grained color appearance. To further refine detailed geometry reshaping, we introduce Global-Local Depth Normalization, enhancing the focus on small local depth changes. Extensive experiments on LLFF, DTU, and Blender datasets demonstrate that DNGaussian outperforms state-of-the-art methods, achieving comparable or better results with significantly reduced memory cost, a 25 × reduction in training time, and over 3000 × faster rendering speed. Code is available at: https://***/Fictionarry/DNGaussian.

关键词： Geometry Training Degradation computer vision Three-dimensional displays Costs Color