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   

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.

How to guess a gradient

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

Learning to Transform for Generalizable Instance-wise Invariance

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.

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

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

Co-domain symmetry for complex-valued deep learning

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

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

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

LO represents motion and semantic categories in addition to object boundaries

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

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