no code implementations • 9 Aug 2023 • Sneha Sree C, Mohammad Al Fahim, Keerthi Ram, Mohanasankar Sivaprakasam
We propose a graph neural network-based transformer based on the Nodeformer architecture to measure and classify the segmentation errors at any point.
1 code implementation • 9 Aug 2023 • Sriprabha Ramanarayanan, Mohammad Al Fahim, Rahul G. S., Amrit Kumar Jethi, Keerthi Ram, Mohanasankar Sivaprakasam
Experiments reveal that our approach 1) adapts on the fly to various unseen configurations up to 32 coils when trained on lower numbers (i. e. 7 to 11) of randomly varying coils, and to 120 deviated unseen configurations when trained on 18 configurations in a single model, 2) matches the performance of coil configuration-specific models, and 3) outperforms configuration-invariant models with improvement margins of around 1 dB / 0. 03 and 0. 3 dB / 0. 02 in PSNR / SSIM for knee and brain data.
1 code implementation • 8 Aug 2023 • Rahul G. S., Sriprabha Ramnarayanan, Mohammad Al Fahim, Keerthi Ram, Preejith S. P, Mohanasankar Sivaprakasam
The self-attention mechanism of the transformer enables transformers to capture long-range dependencies in the images, which might be desirable for accelerated MRI image reconstruction as the effect of undersampling is non-local in the image domain.
1 code implementation • 11 Apr 2023 • Matcha Naga Gayathri, Sriprabha Ramanarayanan, Mohammad Al Fahim, Rahul G S, Keerthi Ram, Mohanasankar Sivaprakasam
We propose SFT-KD-Recon, a student-friendly teacher training approach along with the student as a prior step to KD to make the teacher aware of the structure and capacity of the student and enable aligning the representations of the teacher with the student.