Kushal Vyas
My latest research, papers, and publications.
Latest News
-
Reviewing for NeurIPS‘25.
-
MetaSeg accepted in MICCAI‘25 (ORAL, top 9%).
-
Alpine PyTorch Library is now released. Excited to announce that Alpine - a flexible, distributed and user-friendly library for implicit neural representations is now released! Paper accepted at CVPR 2025, Workshop on Neural Fields beyond Conventional Cameras.
-
Learning Transferable features for Implicit Neural Representations, Kushal Vyas, Ahmed Imtiaz Humayun, Aniket Dashpute, Richard G. Baranuik, Ashok Veeraraghavan and Guha Balakrishnan, accepted at NeurIPS 2024!
Fit pixels, get lables: Meta-learned implciit networks for image segmentation
Kushal Vyas Ashok Veeraraghavan Guha Balakrishnan
MICCAI (ORAL), 2025
We showcase MetaSeg, a scalable meta-learned neural representation (INR) that implicitly captures high-resolution per-pixel segmentation by learning a joint cross-task initialization for the INR. At test-time, the INR reconstructs the input signal, while automatically decoding the underlying semantic segmentation. MetaSeg matches the performance of popular data-driven U-Net models for 2D and 3D brain MRI segmentation with 98% fewer parameters (MICCAI 2025, ORAL, Top 9%)
Learning Transferable Features for Implicit Neural Representations
Kushal Vyas Ahmed Imtiaz Humayun Aniket Dashpute Richard G Baranuik Ashok Veeraraghavan Guha Balakrishnan
NeurIPS, 2024
We showcase STRAINER: A framework to learn transferable and generalizable features for implicit neural representations(INRs) by capturing the underlying low-frequency structural prior from limited data extremely powerful for signal fitting and inverse problems. We use only 10 images as training dataset and achieve superior reconstruction quality compared to recent meta-learing and transformer networks.