检索结果-内蒙古大学图书馆

Rate-Adaptive Generative Semantic Communication Using conditional diffusion models

IEEE WIRELESS COMMUNICATIONS LETTERS 2025年第2期14卷 539-543页

作者： Yang, Pujing Zhang, Guangyi Cai, Yunlong Zhejiang Univ Coll Informat Sci & Elect Engn Hangzhou 310027 Peoples R China Peng Cheng Lab Shenzhen 518071 Peoples R China

Recent advances in deep learning-based joint source-channel coding (DJSCC) have shown promise for end-to-end semantic image transmission. However, most existing schemes primarily focus on optimizing pixel-wise metrics, which often fail to align with human perception, leading to lower perceptual quality. In this letter, we propose a novel generative DJSCC approach using conditional diffusion models to enhance the perceptual quality of transmitted images. Specifically, by utilizing entropy models, we effectively manage transmission bandwidth based on the estimated entropy of transmitted symbols. These symbols are then used at the receiver as conditional information to guide a conditional diffusion decoder in image reconstruction. Our model is built upon the emerging advanced mamba-like linear attention (MLLA) skeleton, which excels in image processing tasks while also offering fast inference speed. Besides, we introduce a multi-stage training strategy to ensure the stability and improve the overall performance of the model. Simulation results demonstrate that our proposed method significantly outperforms existing approaches in terms of perceptual quality.

关键词： Semantic communications conditional diffusion models joint source-channel coding image transmission

来源：评论

学校读者我要写书评

暂无评论

Customized Load Profiles Synthesis for Electricity Customers Based on conditional diffusion models

引用

IEEE TRANSACTIONS ON SMART GRID 2024年第4期15卷 4259-4270页

作者： Wang, Zhenyi Zhang, Hongcai Univ Macau State Key Lab Internet Things Smart City Macau Peoples R China Univ Macau Dept Elect & Comp Engn Macau Peoples R China

Customers' load profiles are critical resources to support data analytics applications in modern power systems. However, there are usually insufficient historical load profiles for data analysis, due to the collection cost and data privacy issues. To address such data shortage problems, load profiles synthesis is an effective technique that provides synthetic training data for customers to build high-performance data-driven models. Nonetheless, it is still challenging to synthesize high-quality load profiles for each customer using generation models trained by the respective customer's data owing to the high heterogeneity of customer load. In this paper, we propose a novel customized load profiles synthesis method based on conditional diffusion models for heterogeneous customers. Specifically, we first convert the customized synthesis into a conditional data generation issue. We then extend traditional diffusion models to conditional diffusion models to realize conditional data generation, which can synthesize exclusive load profiles for each customer according to the customer's load characteristics and application demands. In addition, to implement conditional diffusion models, we design a noise estimation model with stacked residual layers, which improves the generation performance by using skip connections. The attention mechanism is also utilized to better extract the complex temporal dependency of load profiles. Finally, numerical case studies based on a public dataset are conducted to validate the effectiveness and superiority of the proposed method.

关键词： Load modeling Data models Task analysis Power systems Mathematical models Analytical models Numerical models conditional diffusion models data analytics applications deep generative model load profiles synthesis

来源：评论

学校读者我要写书评

暂无评论

Enhancing Rare Object Detection on Roadways Through conditional diffusion models for Data Augmentation

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2024年第11期25卷 19018-19029页

作者： Zhang, Hancheng Hu, Yuanyuan Qian, Zhendong Sha, Jirui Xie, Min Wan, Yuyang Liu, Pengfei Southeast Univ Intelligent Transportat Syst Res Ctr Nanjing 211189 Peoples R China Southeast Univ Bridge Engn Res Ctr Nanjing 211189 Peoples R China Rhein Westfal TH Aachen Inst Highway Engn D-52074 Aachen Germany Beijing Jiaotong Univ Sch Econ & Management Beijing 100091 Peoples R China Aalborg Univ Dept Energy Technol DK-9220 Aalborg Denmark

The detection of rare objects within traffic environments is critically important for the safety and reliability of autonomous driving systems. However, the scarcity of sufficient data and the long-tail effect associated with rare objects pose significant challenges to their detection. To address this issue, this study introduces a conditional diffusion Model, the RareGenDiffuse Model, which generates images of rare objects by taking traffic background images and corresponding bounding box images as inputs. Based on diffusion models, the RareGenDiffuse Model enables control over the category and location of the generated rare objects by adjusting the bounding box images. Experimental results demonstrate that the proposed model offers the advantages of high clarity and controllability. Utilizing the generated rare object dataset significantly enhances the detection outcomes for rare objects. The methodology proposed in this study can effectively reduce the efforts required for data acquisition and labeling, presenting a valuable solution to the challenges of rare object detection in traffic scenarios.

关键词： diffusion models Training Object detection Accuracy Roads Noise measurement Gaussian noise Traffic scene perception rare object detection conditional diffusion models data augmentation

来源：评论

学校读者我要写书评

暂无评论

Unsupervised conditional diffusion models in Video Anomaly Detection for Monitoring Dust Pollution

引用

SENSORS 2024年第5期24卷 1464页

作者： Cai, Limin Li, Mofei Wang, Dianpeng Beijing Inst Technol Sch Math & Stat Beijing 100081 Peoples R China Inner Mongolia Ecol Environm Big Data Co Ltd Hohhot 010010 Peoples R China

Video surveillance is widely used in monitoring environmental pollution, particularly harmful dust. Currently, manual video monitoring remains the predominant method for analyzing potential pollution, which is inefficient and prone to errors. In this paper, we introduce a new unsupervised method based on latent diffusion models. Specifically, we propose a spatio-temporal network structure, which better integrates the spatial and temporal features of videos. Our conditional guidance mechanism samples frames of input videos to guide high-quality generation and obtains frame-level anomaly scores, comparing generated videos with original ones. We also propose an efficient compression strategy to reduce computational costs, allowing the model to perform in a latent space. The superiority of our method was demonstrated by numerical experiments in three public benchmarks and practical application analysis in coal mining over previous SOTA methods with better AUC, of at most over 3%. Our method accurately detects abnormal patterns in multiple challenging environmental monitoring scenarios, illustrating the potential application possibilities in the environmental protection domain and beyond.

关键词： conditional diffusion models dust pollution latent compression video anomaly detection

来源：评论

学校读者我要写书评

暂无评论

A novel conditional diffusion model for joint source-load scenario generation considering both diversity and controllability

引用

APPLIED ENERGY 2025年第PartC期377卷

作者： Zhao, Wei Shao, Zhen Yang, Shanlin Lu, Xinhui Hefei Univ Technol Sch Management Hefei 230009 Peoples R China Minist Educ Key Lab Proc Optimizat & Intelligent Decis Making Hefei 230009 Peoples R China Hefei Univ Technol Philosophy & Social Sci Lab Data Sci & Smart Soc G Minist Educ Hefei 230009 Peoples R China Minist Educ Engn Res Ctr Intelligent Decis Making & Informat S Hefei 230009 Peoples R China

The intermittency of renewable energy and the volatility of multi-energy loads result in multiple joint source- load uncertainties and source-load spatio-temporal mismatch for the scenario generation of deep decarbonized power systems (DDPSs). To address these challenges, a novel model named conditional diffusion-based scenario generation (CDSG) is proposed for controllable joint source-load scenario generation (controllable-JSLSG). The CDSG model incorporates a specialized scenario noise prediction network that includes a conditional spatiotemporal fusion module (CSTFM) and a conditional scenario noise estimation module (CSNEM). Specifically, the CSTFM is devised to excavate the complex spatio-temporal correlations among source-load scenarios, and the CSNEM is utilized to adaptively learn the weights between condition information and source-load scenarios. Then the pretrained CDSG effectively models the nonlinear and irregular spatio-temporal dynamics of source- load, contributing to the controllability and diversity of the generated source-load scenarios. Results verified on real-world datasets demonstrate that CDSG can generate source-load scenarios satisfying dynamic fluctuation properties and frequency-domain characteristics, and ensuring the complex spatio-temporal correlations can be captured. Moreover, compared with other advanced benchmarks, CDSG achieves optimal diversity while maintaining high-quality, indicating its potential for the generation of realistic and diverse joint source-load scenarios. Finally, an optimal dispatch of DDPS is also simulated to evaluate the practical feasibility of the source-load scenarios generated by CDSG.

关键词： Controllable joint source-load scenario generation conditional diffusion models Joint source-load uncertainty Spatio-temporal correlations

来源：评论

学校读者我要写书评

暂无评论

Characterizing the Features of Mitotic Figures Using a conditional diffusion Probabilistic Model 3rd

Characterizing the Features of Mitotic Figures Using a Condi...

引用

3rd Workshop on Deep Generative models for Medical Image Computing and Computer Assisted Intervention (DGM4MICCAI) at the 26th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)

作者： Bahadir, Cagla Deniz Liechty, Benjamin Pisapia, David J. Sabuncu, Mert R. Cornell Univ Ithaca NY 14853 USA Cornell Tech Biomed Engn New York NY 10044 USA Weill Cornell Med Pathol & Lab Med New York NY USA Weill Cornell Med Radiol New York NY USA Cornell Tech Elect & Comp Engn New York NY USA

ISBN: (纸本)9783031537660;9783031537677

Mitotic figure detection in histology images is a hard-to-define, yet clinically significant task, where labels are generated with pathologist interpretations and where there is no "gold-standard" independent ground-truth. However, it is well-established that these interpretation based labels are often unreliable, in part, due to differences in expertise levels and human subjectivity. In this paper, our goal is to shed light on the inherent uncertainty of mitosis labels and characterize the mitotic figure classification task in a human interpretable manner. We train a probabilistic diffusion model to synthesize patches of cell nuclei for a given mitosis label condition. Using this model, we can then generate a sequence of synthetic images that correspond to the same nucleus transitioning into the mitotic state. This allows us to identify different image features associated with mitosis, such as cytoplasm granularity, nuclear density, nuclear irregularity and high contrast between the nucleus and the cell body. Our approach offers a new tool for pathologists to interpret and communicate the features driving the decision to recognize a mitotic figure.

关键词： Mitotic Figure Detection conditional diffusion models

来源：评论

学校读者我要写书评

暂无评论

Attribute conditional diffusion-Augmented Person Re-Identification

Attribute Conditional Diffusion-Augmented Person Re-Identifi...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Nie, Shijie Shi, Ziqiang Liu, Rujie Guo, Song Zhang, Meng Wang, Mengjiao Osamura, Kazuki Septiana, Lina Narishige, Abe Fujitsu Research & Development Center China Fujitsu Limited Japan

ISBN: (纸本)9798350368741

Due to privacy and cost issues, the lack of large-scale labeled datasets limits the advancement of person re-identification. Existing methods use generative adversarial networks or game engine rendering for data augmentation to improve re-identification performance. However, these approaches struggle to maintain realistic images. This paper introduces a novel approach called Identity Diffuser, which uses diffusion models to generate synthetic data for the same identity with different poses. Our proposed framework incorporates identity-specific embeddings and target poses into the diffusion process, enabling the generation of realistic and diverse images that consistently preserve identity features. Guided by pretrained re-identification net and target pose heatmap, the framework learns transformation trajectories through forward and backward denoising steps in the diffusion models. This approach effectively maintains key pedestrian attributes across various poses. Experimental results on the Market1501 and DukeMTMC datasets demonstrate a notable improvement in performance, with a 1.73%/0.80% mAp increase in Market1501/DukeMTMC datasets compared with current state-of-the-art method. When less real data is included, the increment can be 5.1%/1.5%, separately. © 2025 IEEE.

关键词： attribute augmentation conditional diffusion models Person re-identification

来源：评论

学校读者我要写书评

暂无评论

Ship-Go: SAR Ship Images Inpainting via instance-to-image Generative diffusion models

引用

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING 2024年 207卷 203-217页

作者： Zhang, Xin Li, Yang Li, Feng Jiang, Hangzhi Wang, Yanhua Zhang, Liang Zheng, Le Ding, Zegang Beijing Inst Technol Sch Informat & Elect Radar Res Lab Beijing 100081 Peoples R China Beijing Inst Technol Electromagnet Sensing Res Ctr CEMEE State Key Lab Beijing 100081 Peoples R China Beijing Inst Technol Beijing Key Lab Embedded Real Time Informat Proc Beijing 100081 Peoples R China Beijing Inst Technol Chongqing Innovat Ctr Chongqing 401120 Peoples R China Beijing Inst Technol Adv Technol Res Inst Jinan 250300 Shandong Peoples R China Yangtze Delta Reg Acad Beijing Inst Technol Jiaxing 314019 Zhejiang Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing Peoples R China Beijing Inst Technol 5Zhongguancun South St Beijing Peoples R China

We present Ship-Go, an instance-to-image diffusion model, to increase the scale and diversity of the SAR detection datasets. Ship-Go is developed as a multi-conditions denoising diffusion probabilistic model (DDPM), i.e. , it takes the proposed visual instances and environment prompt condition variables as constraints to generate backscatter intensity information for each resolution cell, resulting in inpainting a SAR image and generating the corresponding instance-level annotations, which can be directly employed to train detection models. We demonstrate, for the first time, the ability to place the ship objects at any angle, size, and arrangement in the generated background of multiple specified environment types. Importantly, two image generation scenarios are designed to increase the diversity of objects and backgrounds for the original dataset (i.e. , in-domain augmentation and out-of-domain augmentation). The experiment verifies that the generated detection datasets boost the performance of multiple classical deep detectors in the different cases of insufficient samples. Qualitatively, we find that Ship-Go improves the diversity of the existing dataset, and has sample distribution transferability among multiple datasets. Code and models are available at: https://***/XinZhangRadar/Ship-Go.

关键词： conditional diffusion models Detection datasets generation SAR ship detection

来源：评论

学校读者我要写书评

暂无评论

TF-DiffuSE: Time-Frequency Prior-Conditioned diffusion Model for Speech Enhancement 14

TF-DiffuSE: Time-Frequency Prior-Conditioned Diffusion Model...

引用

14th International Symposium on Chinese Spoken Language Processing

作者： Ding, Wenjun Wang, Xinsheng Gao, Lijian Mao, Qirong Jiangsu Univ Sch Comp Sci & Commun Engn Zhenjiang Jiangsu Peoples R China

ISBN: (纸本)9798331516833;9798331516826

The exceptional generative capabilities of conditional diffusion probabilistic models have demonstrated significant advantages in speech enhancement (SE). However, the introduction of Gaussian noise during the data-to-noise diffusion process fails to consider the critical time-frequency (T-F) structure of audio signals, hindering the quality of generated speech. Moreover, diffusion models typically require numerous denoising steps to achieve high sample quality, leading to increased computational time compared to other generative methods. To address these issues, this paper proposes an efficient T-F prior-conditioned diffusion model for SE, referred to as TF-DiffuSE, which incorporates a fast sampling technique. Specifically, in TF-DiffuSE, a guidance network trained to capture the speech energy distribution is introduced to obtain the T-F prior guidance for the diffusion process. Moreover, a hybrid sampler method is introduced, significantly reducing the number of sampling steps while maintaining speech quality. Comprehensive experimental results demonstrate that the proposed model outperforms existing diffusion-based SE models, achieving superior enhancement performance and exhibiting good generalization in unseen scenarios.

关键词： speech enhancement conditional diffusion models time-frequency prior

来源：评论

学校读者我要写书评

暂无评论

diffusion models for virtual agent facial expression generation in Motivational interviewing 24

Diffusion models for virtual agent facial expression generat...

引用

17th International Conference on Advanced Visual Interfaces (AVI)

作者： Younsi, Nezih Pelachaud, Catherine Chaby, Laurence Sorbonne Univ ISIR Paris France Sorbonne Univ CNRS ISIR Paris France ISIR Paris Cite Paris France

ISBN: (纸本)9798400717642

Motivational interviewing (MI) is a client-centered counseling style that addresses (the client) user's motivation for behavior change. In this paper, we present a behavior generation model for Socially Interactive Agents (SIA) and apply it to an SIA acting as a virtual therapist in (MI). MI defines different types of dialogue acts for therapist and client. It has been shown that therapist builds rapport with their client by adapting their verbal and nonverbal behaviors. Based on the analysis of a human-human MI dataset (AnnoMI), we found co-occurrences between facial expressions and dialogue acts for both therapist and client. Moreover, the therapist adapts their behavior to their client's behavior to favor rapport. Our behavior generation model embeds these co-occurrences as well as such behavior adaptation. To this aim, we build an observation-to-action framework based on a conditional diffusion approach trained on the AnnoMI corpus. Our model learns to generate the virtual therapist's facial expressions conditioned by MI dialogue acts and the client's nonverbal behaviors. We aim to make SIAs more effective in therapy-like interactions, by using user's behaviors in addition to contextual information (i.e. dialogue acts and nonverbal behaviors of both user and agent) to drive the SIA behavior.

关键词： Non-verbal behavior adaptation conditional diffusion models Motivational interviewing

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：