Transformers pay attention to convolutions leveraging emerging properties of ViTs by dual attention-image network

Y Yeganeh, A Farshad, P Weinberger… - Proceedings of the …, 2023 - openaccess.thecvf.com
Although purely transformer-based architectures pretrained on large datasets are introduced
as foundation models for general computer vision tasks, hybrid models that incorporate …

Scenegenie: Scene graph guided diffusion models for image synthesis

A Farshad, Y Yeganeh, Y Chi, C Shen… - Proceedings of the …, 2023 - openaccess.thecvf.com
Text-conditioned image generation has made significant progress in recent years with
generative adversarial networks and more recently, diffusion models. While diffusion models …

Evaluation of pseudo-healthy image reconstruction for anomaly detection with deep generative models: Application to brain FDG PET

R Hassanaly, C Brianceau, M Solal, O Colliot… - arXiv preprint arXiv …, 2024 - arxiv.org
Over the past years, pseudo-healthy reconstruction for unsupervised anomaly detection has
gained in popularity. This approach has the great advantage of not requiring tedious pixel …

VISAGE: Video Synthesis using Action Graphs for Surgery

Y Yeganeh, R Lazuardi, A Shamseddin, E Dari… - arXiv preprint arXiv …, 2024 - arxiv.org
Surgical data science (SDS) is a field that analyzes patient data before, during, and after
surgery to improve surgical outcomes and skills. However, surgical data is scarce …

Anatomy-Aware Masking for Inpainting in Medical Imaging

Y Yeganeh, A Farshad, N Navab - International Workshop on Shape in …, 2023 - Springer
Inpainting has recently been employed as a successful deep-learning technique for
unsupervised model discovery in medical image analysis by taking advantage of the strong …