检索结果-南通市图书馆

An Enhanced GAN for image generation

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第7期80卷 105-118页

作者： Chunwei Tian Haoyang Gao Pengwei Wang Bob Zhang PAMI Research Group University of MacaoMacao999078China School of Software Northwestern Polytechnical UniversityXi’an710129China Yangtze River Delta Research Institute Northwestern Polytechnical UniversityTaicang215400China Research&Development Institute Northwestern Polytechnical UniversityShenzhen518057China

Generative adversarial networks(GANs)with gaming abilities have been widely applied in image ***,gamistic generators and discriminators may reduce the robustness of the obtained GANs in image generation under varying *** the relation of hierarchical information in a generation network and enlarging differences of different network architectures can facilitate more structural information to improve the generation effect for image *** this paper,we propose an enhanced GAN via improving a generator for image generation(EIGGAN).EIGGAN applies a spatial attention to a generator to extract salient information to enhance the truthfulness of the generated *** into relation the context account,parallel residual operations are fused into a generation network to extract more structural information from the different ***,a mixed loss function in a GAN is exploited to make a tradeoff between speed and accuracy to generate more realistic *** results show that the proposed method is superior to popular methods,i.e.,Wasserstein GAN with gradient penalty(WGAN-GP)in terms of many indexes,i.e.,Frechet Inception Distance,Learned Perceptual image Patch Similarity,Multi-Scale Structural Similarity Index Measure,Kernel Inception Distance,Number of Statistically-Different Bins,Inception Score and some visual images for image generation.

关键词： Generative adversarial networks spatial attention mixed loss image generation

On generated artistic styles:image generation experiments with GAN algorithms

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Visual Informatics 2023年第4期7卷 36-40页

作者： Jianheng Xiang School of Design&Innovation China Academy of ArtHangzhouChina

As computer graphics technology supports pursuing a photorealistic style,replicated artworks with a photorealistic style overwhelmingly predominate in the computer-generated art *** with the progression of generative technology,this trend may make generative art a virtual world of photorealistic fake,in which the single criterion of expressive style imperils art into the context of a single boring *** article focuses on the issue of style diversity and its technical feasibility by artistic experiments of generating flower images in *** author insisted that photo both technology and artistic style should not be confined merely for realistic *** proposition was validated in the GAN generation experiment by changing the training materials.

关键词： CG art Virtual realistic image generation Deep learning Machine replication

Data augmentation via joint multi-scale CNN and multi-channel attention for bumblebee image generation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

The Journal of China Universities of Posts and Telecommunications 2023年第3期30卷 32-40,98页

作者： Du Rong Chen Shudong Li Weiwei Zhang Xueting Wang Xianhui Ge Jin Intelligent Manufacturing Electronics Research and Development Center Institute of Microelectronics of the Chinese Academy of SciencesBeijing 100029China School of Integrated Circuits University of Chinese Academy of SciencesBeijing 100049China Institute of Zoology Chinese Academy of SciencesBeijing 100080China Center for Excellence in Biotic Interactions University of Chinese Academy of SciencesBeijing 100049China

The difficulty of bumblebee data collecting and the laborious nature of bumblebee data annotation sometimes result in a lack of training data,which impairs the effectiveness of deep learning based counting *** that it is challenging to produce the detailed background information in the generated bumblebee images using current data augmentation methods,in this paper,a joint multi-scale convolutional neural network and multi-channel attention based generative adversarial network(MMGAN)is *** generates the bumblebee image in accordance with the corresponding density map marking the bumblebee ***,the multi-scale convolutional neural network(CNN)module utilizes multiple convolution kernels to completely extract features of different scales from the input bumblebee image and density *** generate various targets in the generated image,the multi-channel attention module builds numerous intermediate generation layers and attention *** targets are then stacked to produce a bumblebee image with a specific number of *** proposed model obtains the greatest performance in bumblebee image generating tasks,and such generated bumblebee images considerably improve the efficiency of deep learning based counting methods in bumblebee counting applications.

关键词： data augmentation image generation attention mechanism

image generation of Trichomonas Vaginitis Based on Mode Margin Generative Adversarial Networks

在线全文

学校读者我要写书评

暂无评论

Image Generation of Trichomonas Vaginitis Based on Mode Marg...

Prompt learning in computer vision: a survey

第三十九届中国控制会议

作者： Lingjun Meng Feng Jin Wenjuan Zhang Zhui Ge Academy of Automation Beijing Institute of Technology School of Information Science and Engineering Beijing Jiaotong University

Using deep learning to screen for trichomoniasis vaginitis is an important method to assist doctors in ***, scarce medical data always limits the ability of deep learning models, so in order to generate more diverse image data,a Mode Margin Generative Adversarial Network（MMGAN） is proposed. We design a new backbone Generative Adversarial Networks（GAN） and add a model mapping ratio term to it to increase the modes of the generated image, which effectively alleviates the model collapse phenomenon. The network is evaluated on self-built dataset. Experimental results show that the quality and diversity of images generated by MMGAN are better than GAN and WGAN. Moreover, we also provide a basic diagnostic model for trichomoniasis vaginitis and evaluate the effectiveness of the enhanced data in the actual diagnosis. The enhanced data improve the accuracy of the classification model.

关键词： image generation Trichomonas vaginitis Mode margin GAN

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2024年第1期25卷 42-63页

作者： Yiming LEI Jingqi LI Zilong LI Yuan CAO Hongming SHAN Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan UniversityShanghai 200438China Institute of Science and Technology for Brain-Inspired Intelligence Fudan UniversityShanghai 200433China MOE Frontiers Center for Brain Science Fudan UniversityShanghai 200433China Shanghai Center for Brain Science and Brain-Inspired Technology Shanghai 201210China

Prompt learning has attracted broad attention in computer vision since the large pre-trained visionlanguagemodels (VLMs) exploded. Based on the close relationship between vision and language information builtby VLM, prompt learning becomes a crucial technique in many important applications such as artificial intelligencegenerated content (AIGC). In this survey, we provide a progressive and comprehensive review of visual promptlearning as related to AIGC. We begin by introducing VLM, the foundation of visual prompt learning. Then, wereview the vision prompt learning methods and prompt-guided generative models, and discuss how to improve theefficiency of adapting AIGC models to specific downstream tasks. Finally, we provide some promising researchdirections concerning prompt learning.

关键词： Prompt learning Visual prompt tuning(VPT) image generation image classification Artificial intelligence generated content(AIGC)

Restoration of the JPEG Maximum Lossy Compressed Face images with Hourglass Block-GAN

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第3期78卷 2893-2908页

作者： Jongwook Si Sungyoung Kim Department of Computer AI Convergence Engineering Kumoh National Institute of TechnologyGumi39177Korea Department of Computer Engineering Kumoh National Institute of TechnologyGumi39177Korea

In the context of high compression rates applied to Joint Photographic Experts Group(JPEG)images through lossy compression techniques,image-blocking artifacts may *** necessitates the restoration of the image to its original *** challenge lies in regenerating significantly compressed images into a state in which these become ***,this study focuses on the restoration of JPEG images subjected to substantial degradation caused by maximum lossy compression using Generative Adversarial Networks(GAN).The generator in this network is based on theU-Net *** features a newhourglass structure that preserves the characteristics of the deep *** addition,the network incorporates two loss functions to generate natural and high-quality images:Low Frequency(LF)loss and High Frequency(HF)*** loss uses a pretrained VGG-16 network and is configured using a specific layer that best represents *** can enhance the performance in the high-frequency *** contrast,LF loss is used to handle the low-frequency *** two loss functions facilitate the generation of images by the generator,which can mislead the discriminator while accurately generating high-and low-frequency ***,by removing the blocking effects frommaximum lossy compressed images,images inwhich identities could be recognized are *** study represents a significant improvement over previous research in terms of the image resolution performance.

关键词： JPEG lossy compression restoration image generation GAN

An Interactive Collaborative Creation System for Shadow Puppets Based on Smooth Generative Adversarial Networks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第6期79卷 4107-4126页

作者： Cheng Yang Miaojia Lou Xiaoyu Chen Zixuan Ren Department of Industrial Design Hangzhou City UniversityHangzhou310000China College of Computer Science and Technology Zhejiang UniversityHangzhou310000China

Chinese shadow puppetry has been recognized as a world intangible cultural ***,it faces substantial challenges in its preservation and advancement due to the intricate and labor-intensive nature of crafting shadow *** ensure the inheritance and development of this cultural heritage,it is imperative to enable traditional art to flourish in the digital *** paper presents an Interactive Collaborative Creation System for shadow puppets,designed to facilitate the creation of high-quality shadow puppet images with greater *** system comprises four key functions:image contour extraction,intelligent reference recommendation,generation network,and color adjustment,all aimed at assisting users in various aspects of the creative process,including drawing,inspiration,and content ***,we propose an enhanced algorithm called Smooth Generative Adversarial Networks(SmoothGAN),which exhibits more stable gradient training and a greater capacity for generating high-resolution shadow puppet ***,we have built a new dataset comprising high-quality shadow puppet images to train the shadow puppet generation *** qualitative and quantitative experimental results demonstrate that SmoothGAN significantly improves the quality of image generation,while our system efficiently assists users in creating high-quality shadow puppet images,with a SUS scale score of *** study provides a valuable theoretical and practical reference for the digital creation of shadow puppet art.

关键词： Shadow puppets deep learning image generation co-create

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

人工智能在平面设计中的应用研究

Transformers in computational visual media:A survey

设计 2024年第3期9卷 895-901页

作者：宋涛赵欢长春理工大学文学院，吉林长春

随着科技的发展，人工智能的出现为平面设计提供了新的创作方法，也使设计的发展方向与途径发生了改变。平面设计作为艺术创意工作的重要部分之一，也开始探索如何利用人工智能技术提升设计效率与创意水平。本文旨在深入研究人工智能在... 详细信息

随着科技的发展，人工智能的出现为平面设计提供了新的创作方法，也使设计的发展方向与途径发生了改变。平面设计作为艺术创意工作的重要部分之一，也开始探索如何利用人工智能技术提升设计效率与创意水平。本文旨在深入研究人工智能在平面设计中的应用，分析其对平面设计的影响，并探讨未来发展趋势。

关键词：人工智能平面设计图像生成 Artificial Intelligence Graphic Design image generation

来源：博看期刊评论

在线全文

博看期刊

学校读者我要写书评

暂无评论

Computational Visual Media 2022年第1期8卷 33-62页

作者： Yifan Xu Huapeng Wei Minxuan Lin Yingying Deng Kekai Sheng Mengdan Zhang Fan Tang Weiming Dong Feiyue Huang Changsheng Xu NLPR Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100040China School of Artificial Intelligence Jilin UniversityChangchun 130012China Youtu Lab Tencent Inc.Shanghai 200233China CASIA-LLVISION Joint Lab Beijing 100190China

Transformers,the dominant architecture for natural language processing,have also recently attracted much attention from computational visual media researchers due to their capacity for long-range representation and high *** are sequence-to-sequence models,which use a selfattention mechanism rather than the RNN sequential ***,such models can be trained in parallel and can represent global *** study comprehensively surveys recent visual transformer *** categorize them according to task scenario:backbone design,high-level vision,low-level vision and generation,and multimodal *** key ideas are also *** from previous surveys,we mainly focus on visual transformer methods in low-level vision and *** latest works on backbone design are also reviewed in *** ease of understanding,we precisely describe the main contributions of the latest works in the form of *** well as giving quantitative comparisons,we also present image results for low-level vision and generation *** costs and source code links for various important works are also given in this survey to assist further development.

关键词： visual transformer computational visual media(CVM) high-level vision low-level vision image generation multi-modal learning