Uddeshya Upadhyay
Motto - to build cool stuff
I am a Ph.D. candidate at IMPRS-IS Program, Tübingen, where I am part of EML and MIDAS group, and I work closely with Prof. Zeynep Akata and Prof. Sergios Gatidis. I am fascinated by interdisciplinary R&D happening at the intersection of Computer Vision, Machine Learning, Biomedical and Healthcare Informatics. These days I am exploring Bayesian Deep Learning, Uncertainty Estimation, Generative models, Explainable AI (XAI).
I was an undergrad at Computer Science and Engineering@IIT-Bombay.
Here’s a video of Prof. R. Feynman talking about Mathematicians and Physicists. I believe a similar link exists between Researchers and Engineers.
(Best viewed on large-screen devices)
Updates
Jul 17, 2022 | Our work titled “BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks” is accepted at European Conference on Computer Vision (ECCV) 2022! Link to paper / Link to code |
---|---|
Sep 28, 2021 | Our work titled “Robustness via Uncertainty-aware Cycle Consistency” is accepted at Neural Information Processing Systems (NeurIPS) 2021! Link to paper / Link to code |
Sep 2, 2021 | Our work titled “Uncertainty-aware GAN with Adaptive Loss for Robust MRI Enhancement” is accepted at IEEE ICCV Workshop on CV for Automated Medical Diagnosis for oral presentation! Link to paper |
Jul 21, 2021 | Our work “Towards Lower-Dose PET using Physics-Based Uncertainty-Aware Multimodal Learning with Robustness to Out-of-Distribution Data” is accepted at Medical Image Analysis (MedIA) journal! Link to paper |
Jun 15, 2021 | Our work on Uncertainty-guided Progressive GANs is accepted at MICCAI-21! Link to paper / Link to code |