Search Results for author: Natarajan Subramanyam

Found 3 papers, 2 papers with code

WSSL: Weighted Self-supervised Learning Framework For Image-inpainting

1 code implementation25 Nov 2022 Shubham Gupta, Rahul Kunigal Ravishankar, Madhoolika Gangaraju, Poojasree Dwarkanath, Natarajan Subramanyam

To improve the performance of our framework and produce more visually appealing images, we also present a novel loss function for image inpainting.

Image Inpainting Self-Supervised Learning

Robustness to Augmentations as a Generalization metric

1 code implementation16 Jan 2021 Sumukh Aithal K, Dhruva Kashyap, Natarajan Subramanyam

Generalization is the ability of a model to predict on unseen domains and is a fundamental task in machine learning.

Generalization Bounds

Transfer Learning using Neural Ordinary Differential Equations

no code implementations21 Jan 2020 Rajath S, Sumukh Aithal K, Natarajan Subramanyam

A concept of using Neural Ordinary Differential Equations(NODE) for Transfer Learning has been introduced.

Transfer Learning

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