Utkarsh Singhal

I am a PhD student at Berkeley AI Research Lab, which is a part of the EECS department at University of California, Berkeley. I work on computer vision, advised by Professors Stella Yu and Ren Ng.

Email  |  GitHub  |  Google Scholar   

profile photo

Research

I'm interested in building more robust and adaptable deep learning models by taking inspiration from the human brain. My research interests span computer vision, meta-learning, optimization, and robotics.

project image

How to guess a gradient


Utkarsh Singhal, Brian Cheung, Kartik Chandra, Jonathan Ragan-Kelley, Joshua Tenenbaum, Tomaso Poggio, Stella Yu
Optimization for Machine Learning Workshop (OPT2023), NeurIPS, 2023
paper

We use architecture and activations to guess a neural network’s gradients without computing the loss or using backprop.

project image

Learning to Transform for Generalizable Instance-wise Invariance


Utkarsh Singhal, Carlos Esteves, Ameesh Makadia, Stella Yu
International Conference on Computer Vision (ICCV), 2023
paper | code | website

We predict a distribution of transformations for any input image. This can be used for data augmentation, aligning instances, and adapting to out-of-distribution poses.

project image

Multi-Spectral Image Classification with Ultra-Lean Complex-Valued Models


Utkarsh Singhal, Stella X Yu, Zackery Steck, Scott Kangas, Aaron A Reite
(Oral) Humanitarian Aid and Disaster Workshop (HADR), NeurIPS, 2022
paper

We apply our CDS (co-domain symmetry) work on a small and imbalanced dataset in the MSI classification setting.

project image

Co-domain symmetry for complex-valued deep learning


Utkarsh Singhal, Yifei Xing, Stella Yu
Computer Vision and Pattern Recognition (CVPR), 2022
paper | code

We make complex-valued CNNs that are invariant to scale and phase-shifts of the input pixels, and apply it to SAR image classification.

project image

Fourier features let networks learn high frequency functions in low dimensional domains


Matthew Tancik, Pratul Srinivasan, Ben Mildenhall, Sara Fridovich-Keil, Nithin Raghavan, Utkarsh Singhal, Ravi Ramamoorthi, Jonathan Barron, Ren Ng
(Spotlight) NeurIPS, 2021
paper | code | website

We explain why neural networks fail to learn low-dimensional functions and how position encoding (fourier features) help.

project image

LO represents motion and semantic categories in addition to object boundaries


Utkarsh Singhal, Jack Gallant, Mark Lescroart
Journal of Vision, 2019
paper

We studied how the Lateral Occipital cortex represents object boundaries using fMRI.





Source code from Leonid Keselman's fork of Jon Barron's website