检索结果-内蒙古大学图书馆

SDGFormer: An Efficient Convolution Network Structurally Similar to Transformer

学校读者我要写书评

暂无评论

SDGFormer: An Efficient Convolution Network Structurally Sim...

IEEE International Conference on Multimedia and Expo (ICME)

作者： Chaohao Wen Xun Gong School of Computing and Artificial Intelligence SWJTU Chengdu China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education China National Engineering Laboratory of Integrated Transportation Big Data Application Technology SWJTU Chengdu China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province SWJTU Chengdu China

Deep Neural Networks (DNN) have achieved extraordinary success in many visual recognition tasks. Visual Transformer (ViT), which is derived from Natural Language Processing (NLP), has achieved state-of-the-art (SOTA) results on many tasks due to its capability of capturing long-range dependencies in visual data. However, Existing ViT models are challenging to deploy on devices due to their massive computational consumption, huge memory overhead, and reliance on large datasets. In this work, we address these issues by replacing some computationally expensive and memory-intensive modules in ViT with standard Convolutional Neural Network (CNN) modules. Firstly, we propose an efficient Self-Attention module called SDG-Attention (SDGA) with linear space and time complexity, and an economical FeedForward Network (FFN) composed of group convolution and shuffle channel (SFFN). Then, we develop a lightweight CNN model with SDGA and SFFN, SDGFormer, which embraces several priors of ViT and is LayerNorm-Free. We evaluate SDGFormer on ImageNet-1K and Mini-ImageNet, and the SDGFormer-S achieves a comparable top-1 accuracy of 77.6% on ImageNet-1K with 9.1M parameters and 1.6 GFlops regimes. Moreover, our SDGFormer-T achieves SOTA performance on Mini-ImageNet with 83.3% accuracy, demonstrating good generalization on small datasets without extra data.

关键词：

DNN Task Assignment in UAV Networks: A Generative AI Enhanced Multi-Agent Reinforcement Learning Approach

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tang, Xin Chen, Qian Weng, Wenjie Liao, Binhan Wang, Jiacheng Cao, Xianbin Li, Xiaohuan Guangxi University Key Laboratory of Intelligent Networking and Scenario System School of Information and Communication Guilin University of Electronic Technology Guilin541004 China The College of Computing and Data Science Nanyang Technological University 639798 Singapore School of Architecture and Transportation Engineering Guilin University of Electronic Technology Guilin541004 China National Engineering Laboratory for Comprehensive Transportation Big Data Application Technology Guangxi Nanning530001 China College of Computing and Data Science Nanyang Technological University 639798 Singapore School of Electronic and Information Engineering The Key Laboratory of Advanced Technology of Near Space Information System Ministry of Industry and Information Technology of China Beihang University Beijing100191 China

Unmanned Aerial Vehicles (UAVs) possess high mobility and flexible deployment capabilities, prompting the development of UAVs for various application scenarios within the Internet of Things (IoT). The unique capabilities of UAVs give rise to increasingly critical and complex tasks in uncertain and potentially harsh environments. The substantial amount of data generated from these applications necessitates processing and analysis through deep neural networks (DNNs). However, UAVs encounter challenges due to their limited computing resources when managing DNN models. This paper presents a joint approach that combines multiple-agent reinforcement learning (MARL) and generative diffusion models (GDM) for assigning DNN tasks to a UAV swarm, aimed at reducing latency from task capture to result output. To address these challenges, we first consider the task size of the target area to be inspected and the shortest flying path as optimization constraints, employing a greedy algorithm to resolve the subproblem with a focus on minimizing the UAV’s flying path and the overall system cost. In the second stage, we introduce a novel DNN task assignment algorithm, termed GDM-MADDPG, which utilizes the reverse denoising process of GDM to replace the actor network in multi-agent deep deterministic policy gradient (MADDPG). This approach generates specific DNN task assignment actions based on agents’ observations in a dynamic environment. Simulation results indicate that our algorithm performs favorably compared to benchmarks in terms of path planning, Age of Information (AoI), energy consumption, and task load balancing. Copyright © 2024, The Authors. All rights reserved.

关键词： Motion planning

StyleGene: Crossover and Mutation of Region-level Facial Genes for Kinship Face Synthesis

学校读者我要写书评

暂无评论

StyleGene: Crossover and Mutation of Region-level Facial Gen...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Hao Li Xianxu Hou Zepeng Huang Linlin Shen Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University School of AI and Advanced Computing Xi'an Jiaotong-Liverpool University Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University

High-fidelity kinship face synthesis has many potential applications, such as kinship verification, missing child identification, and social media analysis. However, it is challenging to synthesize high-quality descendant faces with genetic relations due to the lack of large-scale, high-quality annotated kinship data. This paper proposes RFG (Region-level Facial Gene) extraction framework to address this issue. We propose to use IGE (Image-based Gene Encoder), LGE (Latent-based Gene Encoder) and Gene Decoder to learn the RFGs of a given face image, and the relationships between RFGs and the latent space of Style-GAN2. As cycle-like losses are designed to measure the $\mathcal{L}_data$ distances between the output of Gene Decoder and image encoder, and that between the output of LGE and IGE, only face images are required to train our framework, i.e. no paired kinship face data is required. Based upon the proposed RFGs, a crossover and mutation module is further designed to inherit the facial parts of parents. A Gene Pool has also been used to introduce the variations into the mutation of RFGs. The diversity of the faces of descendants can thus be significantly increased. Qualitative, quantitative, and subjective experiments on FIW, TSKinFace, and FF-databases clearly show that the quality and diversity of kinship faces generated by our approach are much better than the existing state-of-the-art methods.

关键词：

Masked Motion Encoding for Self-Supervised Video Representation Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Sun, Xinyu Chen, Peihao Chen, Liangwei Li, Changhao Li, Thomas H. Tan, Mingkui Gan, Chuang South China University of Technology China Information Technology R&d Innovation Center Peking University China UMass Amherst United States MIT-IBM Watson Ai Lab United States Key Laboratory of Big Data and Intelligent Robot Ministry of Education Peking University Shenzhen Graduate School China

How to learn discriminative video representation from unlabeled videos is challenging but crucial for video analysis. The latest attempts seek to learn a representation model by predicting the appearance contents in the masked regions. However, simply masking and recovering appearance contents may not be sufficient to model temporal clues as the appearance contents can be easily reconstructed from a single frame. To overcome this limitation, we present Masked Motion Encoding (MME), a new pretraining paradigm that reconstructs both appearance and motion information to explore temporal clues. In MME, we focus on addressing two critical challenges to improve the representation performance: 1) how to well represent the possible long-term motion across multiple frames;and 2) how to obtain fine-grained temporal clues from sparsely sampled videos. Motivated by the fact that human is able to recognize an action by tracking objects' position changes and shape changes, we propose to reconstruct a motion trajectory that represents these two kinds of change in the masked regions. Besides, given the sparse video input, we enforce the model to reconstruct dense motion trajectories in both spatial and temporal dimensions. Pre-trained with our MME paradigm, the model is able to anticipate longterm and fine-grained motion details. Code is available at https://***/XinyuSun/MME. Copyright © 2022, The Authors. All rights reserved.

关键词： Signal encoding

Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is available at this url. © 2024, CC BY.

关键词： Semantics

Structural Entities Extraction and Patient Indications Incorporation for Chest X-ray Report Generation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Kang Ma, Zhuoqi Kang, Xiaolu Zhong, Zhusi Jiao, Zhicheng Baird, Grayson Bai, Harrison Miao, Qiguang School of Computer Science and Technology Xidian University Xi’an China Xi’an Key Laboratory of Big Data and Intelligent Vision Xi’an China Key Laboratory of Collaborative Intelligence Systems Ministry of Education Xidian University Xi’an China Warren Alpert Medical School Brown University Providence United States School of Electronic Engineering Xidian University Xi’an China Department of Radiology and Radiological Sciences Johns Hopkins University School of Medicine Baltimore United States

The automated generation of imaging reports proves invaluable in alleviating the workload of radiologists. A clinically applicable reports generation algorithm should demonstrate its effectiveness in producing reports that accurately describe radiology findings and attend to patient-specific indications. In this paper, we introduce a novel method, Structural Entities extraction and patient indications Incorporation (SEI) for chest X-ray report generation. Specifically, we employ a structural entities extraction (SEE) approach to eliminate presentation-style vocabulary in reports and improve the quality of factual entity sequences. This reduces the noise in the following cross-modal alignment module by aligning X-ray images with factual entity sequences in reports, thereby enhancing the precision of cross-modal alignment and further aiding the model in gradient-free retrieval of similar historical cases. Subsequently, we propose a cross-modal fusion network to integrate information from X-ray images, similar historical cases, and patient-specific indications. This process allows the text decoder to attend to discriminative features of X-ray images, assimilate historical diagnostic information from similar cases, and understand the examination intention of patients. This, in turn, assists in triggering the text decoder to produce high-quality reports. Experiments conducted on MIMIC-CXR validate the superiority of SEI over state-of-the-art approaches on both natural language generation and clinical efficacy metrics. Copyright © 2024, The Authors. All rights reserved.

关键词： Extraction

Research on Experimental System and Method for Electric Vehicle Charging Behavior Detection

学校读者我要写书评

暂无评论

Research on Experimental System and Method for Electric Vehi...

Chinese Automation Congress (CAC)

作者： Hongyu Long Xiaosheng Zhan Yuansen Xu Jianbo Yu Tian Tian Yongzhong Zhou School of Automation/School of Industrial Internet and Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Chongqing China School of Automation Chongqing University of Posts and Telecommunications Chongqing China Economic and Technical Research Institute of State Grid Chongqing Electric Power Company Chongqing China

Before the charging behavior occurs, drivers often make charging decisions motivated by range anxiety. Traditional research on charging behavior mainly relies on psychological questionnaires and big data analysis, but these methods are subjective and limited. Therefore, this paper uses physiological signal studies as a supplement to provide objective and quantitative indicators. In this paper, by building an experimental platform and designing an experimental scheme, the electroencephalogram, electrocardiogram, electrodermal and electromyography signals of the subjects during simulated driving were collected. Through data processing and analysis, it is found that the EEG signal, ECG signal, EDA signal and EMG signal will change after the driver is stimulated by insufficient driving range. The experimental results show that there is a certain correlation between the driver's range anxiety state and physiological information, indicating that physiological signals can be used as an effective tool to evaluate and study range anxiety, and also provide a new solution for the driver's state detection before charging electric vehicles, which is of great significance for the popularization and promotion of electric vehicles.

关键词：

Pareto-aware Neural Architecture Generation for Diverse Computational Budgets

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Guo, Yong Chen, Yaofo Zheng, Yin Chen, Qi Zhao, Peilin Chen, Jian Huang, Junzhou Tan, Mingkui The School of Software Engineering South China University of Technology China Max Planck Institute for Informatics Germany The Weixin Group Tencent China The School of Computer Science The University of Adelaide Australia Tencent AI Lab Tencent China The Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China The Pazhou Laboratory Guangzhou China

Designing feasible and effective architectures under diverse computational budgets, incurred by different applications/devices, is essential for deploying deep models in real-world applications. To achieve this goal, existing methods often perform an independent architecture search process for each target budget, which is very inefficient yet unnecessary. More critically, these independent search processes cannot share their learned knowledge (i.e., the distribution of good architectures) with each other and thus often result in limited search results. To address these issues, we propose a Pareto-aware Neural Architecture Generator (PNAG) which only needs to be trained once and dynamically produces the Pareto optimal architecture for any given budget via inference. To train our PNAG, we learn the whole Pareto frontier by jointly finding multiple Pareto optimal architectures under diverse budgets. Such a joint search algorithm not only greatly reduces the overall search cost but also improves the search results. Extensive experiments on three hardware platforms (i.e., mobile device, CPU, and GPU) show the superiority of our method over existing methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Pareto principle

Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Yang, Zhiyong Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China School of Cyber Science and Tech. Sun Yat-sen University Shenzhen Campus China

Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is available at this url. © 2024, CC BY.

关键词：