MEDDAP: Medical Dataset Enhancement via Diversified Augmentation Pipeline

1 code implementation • 25 Mar 2024 • Yasamin Medghalchi, Niloufar Zakariaei, Arman Rahmim, Ilker Hacihaliloglu

Moreover, ensuring that the model remains robust across various scenarios of image capture is crucial in medical domains, especially when dealing with ultrasound images that vary based on the settings of different devices and the manual operation of the transducer.

Benchmarking Robustness to Text-Guided Corruptions

1 code implementation • 6 Apr 2023 • Mohammadreza Mofayezi, Yasamin Medghalchi

Unlike other works that use synthetic or hand-picked data for benchmarking, we use diffusion models as they are generative models capable of learning to edit images while preserving their semantic content.

Benchmarking Data Augmentation

A generic diffusion-based approach for 3D human pose prediction in the wild

1 code implementation • 11 Oct 2022 • Saeed Saadatnejad, Ali Rasekh, Mohammadreza Mofayezi, Yasamin Medghalchi, Sara Rajabzadeh, Taylor Mordan, Alexandre Alahi

Predicting 3D human poses in real-world scenarios, also known as human pose forecasting, is inevitably subject to noisy inputs arising from inaccurate 3D pose estimations and occlusions.

Denoising Human Pose Forecasting +2