Hybrid deep learning framework based on EfficientViT for classification of gastrointestinal diseases by Vishesh Tanwar, Bhisham Sharma, Dhirendra Prasad Yadav, Abolfazl Mehbodniya

“…At the same time, it includes the capacity of the ViT model to recognize the context of images of the GI tract for the detection of slight disease patterns and precursors of disease diffusion. Furthermore, we designed a dual-block in which input is divided into two parts (q1, q2) to better optimize the model q1 processed through an EfficientNet for local details and a q2 through encoder block for capturing the global dependencies, which enables EfficientViT to pay attention to multiple image regions simultaneously. …”
Get full text

Multimodal diffusion framework for collaborative text image audio generation and applications by Junhua Wang, Ouya Zhang, Yuan Jiang

“…Abstract This paper presents a novel framework for collaborative generation across text, image, and audio modalities using an enhanced diffusion model architecture. We introduce a Hierarchical Cross-modal Alignment Network that establishes unified representations while preserving modality-specific characteristics, and a Cross-modal Conditional Diffusion Model that enables flexible generation pathways through innovative conditional embedding and attention-guided mechanisms. …”
Get full text

CaloDREAM – Detector response emulation via attentive flow matching by Luigi Favaro, Ayodele Ore, Sofia Palacios Schweitzer, Tilman Plehn

Get full text

Menstrual cycle inspired latent diffusion model for image augmentation in energy production by Gamal M. Mahmoud, Mostafa Elbaz, Wael Said, Amira A. Elsonbaty

“…This paper introduces menstrual cycle-inspired latent diffusion model (MCI-LDM), a novel framework that addresses these challenges with three key modifications. …”
Get full text

Advancing Persistent Character Generation: Comparative Analysis of Fine-Tuning Techniques for Diffusion Models by Luca Martini, Saverio Iacono, Daniele Zolezzi, Gianni Viardo Vercelli

“…It excels in low VRAM contexts due to its targeted fine-tuning of low-rank matrices within cross-attention layers, enabling faster training and efficient parameter tweaking. …”
Get full text

Modeling Homogeneous, Stratified, and Diffusion Combustion in Hydrogen SI Engines Using the Wiebe Approach by Oleksandr Osetrov, Rainer Haas

“…This study further develops the model by accounting for the combined influence of the mixture composition and engine speed, mixture stratification, and the effects of injection and ignition parameters on premixed and diffusion combustion. Special attention is given to combustion modeling in an engine with single injection and jet-guided operation.…”
Get full text

SVPDSA: Selective View Perception Data Synthesis With Annotations Using Lightweight Diffusion Network by S. Raghavendra, Vijayalakshmi, Vainidhi, S. K. Abhilash, Venu Madhav Nookala, P. V. Arun Kumar, Ramyashree

“…A compressed Unet-based diffusion model, pre-trained on the LAION-5B dataset, serves as the foundation for efficient text-to-image synthesis. …”
Get full text

Denoising diffusion probabilistic models for addressing data limitations in chest X-ray classification by Evi M.C. Huijben, Josien P.W. Pluim, Maureen A.J.M. van Eijnatten

“…To address these challenges, there has been a growing interest in the use of deep generative models to create synthetic training data, with denoising diffusion probabilistic models (DDPMs) recently gaining attention for their ability to produce realistic and high-quality images. …”
Get full text

SGM-EMA: Speech Enhancement Method Score-Based Diffusion Model and EMA Mechanism by Yuezhou Wu, Zhiri Li, Hua Huang

“…This paper proposes a U-Net architecture using a score-based diffusion model and an efficient multi-scale attention mechanism (EMA) for the speech enhancement task. …”
Get full text

Swin-Diff: a single defocus image deblurring network based on diffusion model by Hanyan Liang, Shuyao Chai, Xixuan Zhao, Jiangming Kan

“…Our results validate the effectiveness of combining diffusion models with hierarchical attention mechanisms for high-quality defocus blur removal.…”
Get full text

Contour wavelet diffusion – a fast and high-quality facial expression generation model by Chenwei Xu, Yuntao Zou

“…To address these limitations, we propose a contour wavelet diffusion model that accelerates both training and inference speeds. …”
Get full text

Bibliometric cartography of data science: a large-scale analysis on knowledge integration and diffusion by Hongkan Chen, Jinchang Liu, Win-bin Huang, Yi Bu

“…The diffusion process is driven by both viral and broadcasting adopters, with the former facilitating early-stage dissemination, although a “damping” effect emerges as dissemination efficiency gradually declines. …”
Get full text

Dynamically Tunable Multidimensional Feature Focusing and Diffusion Networks for Water Surface Debris Detection by Chong Zhang, Jie Yue, Jianglong Fu

“…Furthermore, a Focal-Diffuse Feature Pyramid Network (FD-FPN) was introduced to accurately capture and integrate key feature information through focused feature fusion techniques while utilizing cross-scale diffusion analysis to efficiently transfer and enhance feature information across different scales. …”
Get full text

A Mathematical Survey of Image Deep Edge Detection Algorithms: From Convolution to Attention by Gang Hu

“…Beginning with Sobel and Canny’s kernel-based approaches, we trace the shift to data-driven CNNs like Holistically Nested Edge Detection (HED) and Bidirectional Cascade Network (BDCN), which leverage multi-scale supervision and achieve ODS (Optimal Dataset Scale) scores 0.788 and 0.806, respectively. Attention mechanisms, as in EdgeNAT (ODS 0.860) and RankED (ODS 0.824), enhance global context, while generative models like GED (ODS 0.870) achieve state-of-the-art precision via diffusion and GAN frameworks. …”
Get full text

A Lightweight Conditional Diffusion Segmentation Network Based on Deformable Convolution for Surface Defect Detection by Jiusheng Chen, Yibo Zhao, Haibing Wang

“…Surface defect detection is crucial to industrial manufacturing and research for surface defects has drawn much attention. However, defects in industrial environment are very diverse. …”
Get full text

Attention-enhanced residual U-Net: lymph node segmentation method with bimodal MRI images by Juping Qiu, Chunxia Chen, Ming Li, Jingde Hong, Binhua Dong, Shangyue Xu, Yongping Lin

“…The DWI and T2 images were fused and inputted into U-Net. The efficient channel attention (ECA) module was added to U-Net. …”
Get full text

Enhancing Atmospheric Turbulence Phase Screen Generation with an Improved Diffusion Model and U-Net Noise Generation Network by Hangning Kou, Min Wan, Jingliang Gu

“…Additionally, a self-attention module strengthens the model’s ability to learn phase screen features. …”
Get full text

DCT-DiffPose: A Lightweight Diffusion Model With Multi-Hypothesis for 3D Human Pose Estimation by Linzhan Zhong, Fangni Chen, Bolun Zheng, Rui Feng, Lei Zhang, Jian Wan

“…3D human pose estimation is a crucial task in computer vision with extensive applications, yet it remains challenging due to depth ambiguity and constraints on computational efficiency. In this paper, we propose DCT-DiffPose, a novel framework that integrates a diffusion model with Confidence and Consistency-based Multi-Hypothesis Aggregation (CCMA). …”
Get full text

Evaluating Nanofiltration and Reverse Osmosis Membranes for Pharmaceutically Active Compounds Removal: A Solution Diffusion Model Approach by Yonghyun Shin, Tae-Mun Hwang, Sook-Hyun Nam, Eunju Kim, JeongBeen Park, Yong-Jun Choi, Homin Kye, Jae-Wuk Koo

“…To address these issues, nanofiltration (NF) and reverse osmosis (RO) membrane technologies have gained attention. This study aims to evaluate the performance of NF and RO membranes in removing TrOCs from wastewater and develop a predictive model using the Solution Diffusion Model. …”
Get full text

MGLI-Former: a multi-scale and global-local information interactive attention transformer for urban shantytown extraction by Shouhang Du, Shaoyu Wang, Yuhao Hua, Shu Peng, Fei Qin, Xue Li, Yufei Wu

“…Shantytowns, characterized by poor living conditions and simple houses, necessitate efficient extraction and analysis for urban planning. …”
Get full text