Search Results for author: Utkarsh Singhal

Found 6 papers, 2 papers with code

How to guess a gradient

no code implementations7 Dec 2023 Utkarsh Singhal, Brian Cheung, Kartik Chandra, Jonathan Ragan-Kelley, Joshua B. Tenenbaum, Tomaso A. Poggio, Stella X. Yu

We study how to narrow the gap in optimization performance between methods that calculate exact gradients and those that use directional derivatives.

Learning to Transform for Generalizable Instance-wise Invariance

1 code implementation ICCV 2023 Utkarsh Singhal, Carlos Esteves, Ameesh Makadia, Stella X. Yu

However, too much or too little invariance can hurt, and the correct amount is unknown a priori and dependent on the instance.

Data Augmentation

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

no code implementations21 Nov 2022 Utkarsh Singhal, Stella X. Yu, Zackery Steck, Scott Kangas, Aaron A. Reite

Multi-spectral imagery is invaluable for remote sensing due to different spectral signatures exhibited by materials that often appear identical in greyscale and RGB imagery.

Data Augmentation Humanitarian +2

Co-domain Symmetry for Complex-Valued Deep Learning

no code implementations CVPR 2022 Utkarsh Singhal, Yifei Xing, Stella X. Yu

We study complex-valued scaling as a type of symmetry natural and unique to complex-valued measurements and representations.

HyperReal: Complex-Valued Layer Functions For Complex-Valued Scaling Invariance

no code implementations1 Jan 2021 Utkarsh Singhal, Yifei Xing, Stella Yu

SurReal complex-valued networks adopt a manifold view of complex numbers and derive a distance metric that is invariant to complex scaling.

Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains

13 code implementations NeurIPS 2020 Matthew Tancik, Pratul P. Srinivasan, Ben Mildenhall, Sara Fridovich-Keil, Nithin Raghavan, Utkarsh Singhal, Ravi Ramamoorthi, Jonathan T. Barron, Ren Ng

We show that passing input points through a simple Fourier feature mapping enables a multilayer perceptron (MLP) to learn high-frequency functions in low-dimensional problem domains.

Cannot find the paper you are looking for? You can Submit a new open access paper.