Search Results for author: Mokshagna Sai Teja Karanam

Found 2 papers, 0 papers with code

EfficientMorph: Parameter-Efficient Transformer-Based Architecture for 3D Image Registration

no code implementations16 Mar 2024 Abu Zahid Bin Aziz, Mokshagna Sai Teja Karanam, Tushar Kataria, Shireen Y. Elhabian

Secondly, feature similarities across attention heads that were recently found in multi-head attention architectures indicate a significant computational redundancy, suggesting that the capacity of the network could be better utilized to enhance performance.

 Ranked #1 on Medical Image Registration on OASIS (val dsc metric)

Computational Efficiency Image Registration +1

ADASSM: Adversarial Data Augmentation in Statistical Shape Models From Images

no code implementations6 Jul 2023 Mokshagna Sai Teja Karanam, Tushar Kataria, Krithika Iyer, Shireen Elhabian

However, these augmentation methods focus on shape augmentation, whereas deep learning models exhibit image-based texture bias resulting in sub-optimal models.

Anatomy Data Augmentation +2

Cannot find the paper you are looking for? You can Submit a new open access paper.