10 citations · 22 across the 17 of their papers we have counts for
18 papers
Uncertainty-aware Test-Time Training (UT) for Efficient On-the-fly Domain Adaptive Dense Regression
Uddeshya Upadhyay
Deep neural networks (DNNs) are increasingly being used in autonomous systems. However, DNNs do not generalize well to domain shift. Adapting to a continuously evolving environment…
Perceiving Beyond Language Priors: Enhancing Visual Comprehension and Attention in Multimodal Models
Aarti Ghatkesar, Ganesh Venkatesh
Achieving deep alignment between vision and language remains a central challenge for Multimodal Large Language Models (MLLMs). These models often fail to fully leverage visual inpu…
HypUC: Hyperfine Uncertainty Calibration with Gradient-boosted Corrections for Reliable Regression on Imbalanced Electrocardiograms
Uddeshya Upadhyay, Sairam Bade, Arjun Puranik +8
The automated analysis of medical time series, such as the electrocardiogram (ECG), electroencephalogram (EEG), pulse oximetry, etc, has the potential to serve as a valuable tool f…
ProbVLM: Probabilistic Adapter for Frozen Vision-Language Models
Uddeshya Upadhyay, Shyamgopal Karthik, Massimiliano Mancini +1
Large-scale vision-language models (VLMs) like CLIP successfully find correspondences between images and text. Through the standard deterministic mapping process, an image or a tex…
USIM-DAL: Uncertainty-aware Statistical Image Modeling-based Dense Active Learning for Super-resolution
Vikrant Rangnekar, Uddeshya Upadhyay, Zeynep Akata +1
Dense regression is a widely used approach in computer vision for tasks such as image super-resolution, enhancement, depth estimation, etc. However, the high cost of annotation and…
Likelihood Annealing: Fast Calibrated Uncertainty for Regression
Uddeshya Upadhyay, Jae Myung Kim, Cordelia Schmidt +2
Recent advances in deep learning have shown that uncertainty estimation is becoming increasingly important in applications such as medical imaging, natural language processing, and…
Towards Automating Retinoscopy for Refractive Error Diagnosis
Aditya Aggarwal, Siddhartha Gairola, Uddeshya Upadhyay +6
Refractive error is the most common eye disorder and is the key cause behind correctable visual impairment, responsible for nearly 80% of the visual impairment in the US. Refractiv…
BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks
Uddeshya Upadhyay, Shyamgopal Karthik, Yanbei Chen +2
High-quality calibrated uncertainty estimates are crucial for numerous real-world applications, especially for deep learning-based deployed ML systems. While Bayesian deep learning…
The Manifold Hypothesis for Gradient-Based Explanations
Sebastian Bordt, Uddeshya Upadhyay, Zeynep Akata +1
When do gradient-based explanation algorithms provide perceptually-aligned explanations? We propose a criterion: the feature attributions need to be aligned with the tangent space…
Robustness via Uncertainty-aware Cycle Consistency
Uddeshya Upadhyay, Yanbei Chen, Zeynep Akata
Unpaired image-to-image translation refers to learning inter-image-domain mapping without corresponding image pairs. Existing methods learn deterministic mappings without explicitl…
Uncertainty-aware GAN with Adaptive Loss for Robust MRI Image Enhancement
Uddeshya Upadhyay, Viswanath P. Sudarshan, Suyash P. Awate
Image-to-image translation is an ill-posed problem as unique one-to-one mapping may not exist between the source and target images. Learning-based methods proposed in this context…
Towards Lower-Dose PET using Physics-Based Uncertainty-Aware Multimodal Learning with Robustness to Out-of-Distribution Data
Viswanath P. Sudarshan, Uddeshya Upadhyay, Gary F. Egan +2
Radiation exposure in positron emission tomography (PET) imaging limits its usage in the studies of radiation-sensitive populations, e.g., pregnant women, children, and adults that…
Uncertainty-Guided Progressive GANs for Medical Image Translation
Uddeshya Upadhyay, Yanbei Chen, Tobias Hepp +2
Image-to-image translation plays a vital role in tackling various medical imaging tasks such as attenuation correction, motion correction, undersampled reconstruction, and denoisin…
A Mixed-Supervision Multilevel GAN Framework for Image Quality Enhancement
Uddeshya Upadhyay, Suyash Awate
Deep neural networks for image quality enhancement typically need large quantities of highly-curated training data comprising pairs of low-quality images and their corresponding hi…
Uncertainty-aware Generalized Adaptive CycleGAN
Uddeshya Upadhyay, Yanbei Chen, Zeynep Akata
Unpaired image-to-image translation refers to learning inter-image-domain mapping in an unsupervised manner. Existing methods often learn deterministic mappings without explicitly…
Transformer Based Reinforcement Learning For Games
Uddeshya Upadhyay, Nikunj Shah, Sucheta Ravikanti +1
Recent times have witnessed sharp improvements in reinforcement learning tasks using deep reinforcement learning techniques like Deep Q Networks, Policy Gradients, Actor Critic met…
Robust Super-Resolution GAN, with Manifold-based and Perception Loss
Uddeshya Upadhyay, Suyash P. Awate
Super-resolution using deep neural networks typically relies on highly curated training sets that are often unavailable in clinical deployment scenarios. Using loss functions that…
Removal of Batch Effects using Generative Adversarial Networks
Uddeshya Upadhyay, Arjun Jain
Many biological data analysis processes like Cytometry or Next Generation Sequencing (NGS) produce massive amounts of data which needs to be processed in batches for down-stream an…