I am an ELLIS PhD Student advised by Prof. Bernt Schiele (Max Planck Institute of Informatics, Saarbrücken) and Prof. Francesco Locatello (ISTA). During the course of my PhD I shall be associated with both the Max Planck Institute for Informatics and Institute of Science and Technology, Austria.
Previously, I was a Research Fellow at Microsoft Research (MSR), India in the Technology for Emerging Markets group, where I worked on applications of Computer Vision, Image Processing and Machine Learning to developing low-cost diagnostic solutions for healthcare. Before that, I worked as a Research Intern at Adobe Inc. in the Media and Data Science Research Group on image understanding tasks.
I completed my Master's and B.Tech with Honours in May, 2020 at IIIT Hyderabad, where I was advised by Prof. PJ Narayanan. My work was mainly on learning robust unsupervised style representations for image recognition and retrieval tasks.
Current Research: I am broadly interested in Artificial Intelligence (Machine Learning), Computer Vision, Image Processing, Natural Language Processing and their applications to real-world problems. I am particularly interested in building reliable (robust) systems that model visual perception with limited supervision. To this end, for my PhD I will be exploring two major directions:
When not working on my research, I like to play the piano and guitar, listen to music, read non-fiction, drive motorcycles, and go for a run or hike. I also am really fascinated by paradoxes, can find some here. (I wish I had Hermione's Time-Turner to do much more in a day as much as I'd like to.) (see more at Personal)
Pre-print, Feb. 2026
arxiv / code / presentation / bibtex
DAVE is a distribution-aware attribution method for Vision Transformers that produces stable, high-resolution pixel-level explanations while reducing patch/grid artifacts common in ViT saliency maps.
International Conference on Learning Representations (ICLR), 2025
OpenReview / arxiv / code / bibtex
We show that training details of a pre-trained model's classification layer (<10% of parameters) play a crucial role in post-hoc explanations, and present simple adjustments that significantly enhance explanation quality across multiple visual pre-training frameworks.
International Joint Conferences on Artificial Intelligence (IJCAI), 2020
IJCAI_Proceedings / pdf / bibtex
Improving similarity propagation to improve one-shot and few-shot image segmentation.
IEEE Winter Conference on Applications of Computer Vision (WACV '20), 2020
code / project_page / paper / supp_material / bibtex
An unsupervised protocol for learning a neural embedding of visual style of images. The proposed protocol does not leverage categorical labels but a proxy measure for finding stylistically similar and dissimilar images.
International Conference on Multimedia Modelling (MMM '18), 2018
project_page / pdf / bibtex
A data driven method for color-consistent sky search and replacement. This technology does not require the use of complex color transfer techniques.
*Both authors contributed equally towards this work.
IEEE Winter Conference on Applications of Computer Vision (WACV '25), 2025
Open Access / code / bibtex
Improving the SmartKC image processing pipeline, making it more robust and accurate.
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT), Volume 6, Issue 3, 2022
code / project_page / pdf
We automate retinoscopy using a smartphone attached to a retinoscope, achieving 91.0% sensitivity and 0.75D mean error for refractive error screening.
IEEE Engineering in Medicine & Biology Society (EMBC), 2022
A dual-head CNN for classifying keratoconus on SmartKC heatmaps, achieving 91.3% sensitivity and 94.2% specificity using a 2-stage transfer learning strategy.
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT), Volume 5, Issue 4, 2021
code / project_page / pdf / demo_video
SmartKC is a low-cost smartphone-based corneal topographer. It provides a low-cost solution for the mass screening of keratoconus at scale.
IEEE Engineering in Medicine & Biology Society (EMBC), 2021
RespireNet is a CNN-based model with novel techniques—device specific fine-tuning, concatenation-based augmentation, blank region clipping, and smart padding. We improve upon the state-of-the-art on ICBHI dataset by 2.2%.
ACM SIGIR, 2018
Detecting clickbaits using Deep Learning.
For my Master's research I was supervised by Prof. P. J. Narayanan at CVIT at IIIT Hyderabad. My research was on the following two tasks (1) representation learning for image style search and retrieval, and (2) color consistent background replacement.
Master's Thesis, IIIT Hyderabad, 2020
Worked as a Teaching Assistant at Saarland University for the courses listed below. The duties involved setting up questions for assignments, examinations and paper corrections.
Worked as a Teaching Assistant at IIIT Hyderabad for the courses listed below. The duties involved taking regular tutorials, paper corrections, setting up questions for assignments and conducting evaluations.
I contribute actively to open source organizations — Scilab and LibreOffice. I have been working with Scilab for the past 3 years now. My proposals were selected twice (2017, 2018) as a project for GSoC (Google Summer of Code) Program.
Google Summer of Code 2017
Project Details: Implemented a C/C++ wrapper for Matlab MEX-API on current API Scilab.
Google Summer of Code 2018
Project Details: Implemented a DEMO in C/C++ and Scilab as a working example for the MEX Library in Scilab.