Research

Towards causally linking architectural parametrizations to algorithmic bias in neural networks

Hao Liang, Josue Ortega Caro, Vikram Maheshri, Ankit B. Patel, Guha Balakrishnan

In submission.

paper

SplineCam: Exact Visualization of Deep Neural Network Geometry and Decision Boundaries

Ahmed Imtiaz Humayun, Randall Balestriero, Guha Balakrishnan, Richard Baraniuk

In submission.

WIRE: Wavelet Implicit Neural Representations

Vishwanath Saragadam, Daniel LeJeune, Jasper Tan, Guha Balakrishnan, Ashok Veeraraghavan, Richard G. Baraniuk

In submission.

website, paper, code

MINER: Multiscale Implicit Neural Representations

Vishwanath Saragadam, Jasper Tan, Guha Balakrishnan, Richard Baraniuk, Ashok Veeraraghavan

ECCV 2022

paper, code

Latent Rayleigh EigenDirections for controlled GAN Synthesis

G. Balakrishnan, R. Gadde, A. Martinez, P. Perona

ECCV 2022

paper, code

Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Learning

D. Zietlow, M. Lohaus, G. Balakrishnan, M. Kleindessner, F. Locatello, B. Scholkopf, C. Russell

CVPR 2022.

paper

Better aggregation in test-time augmentation

D. Shanmugam, D. Blalock, G. Balakrishnan, J. Guttag

ICCV 2021 (oral)

paper

Matched sample selection for face datasets via GAN projection

C. Singh, G. Balakrishnan, P. Perona

CVPR 2021 Causality in Vision Workshop

paper, code

Towards causal benchmarking of face analysis algorithms

G. Balakrishnan, Y. Xiong, W. Xia, P. Perona

ECCV 2020

paper

Painting Many Pasts: Synthesizing Time Lapse Videos of Paintings

A. Zhao, G. Balakrishnan, K.M. Lewis, F. Durand, J. Guttag, A. V. Dalca

CVPR 2020

paper, site, code

Visual Deprojection: Probabilistic Recovery of Collapsed Dimensions in Images and Videos

G. Balakrishnan, A. V. Dalca, A. Zhao, J. Guttag, F. Durand, W.T. Freeman

ICCV 2019

paper

Press:

mit news, engadget, petapixel, science daily, techspot

Synthesizing Images of Humans in Unseen Poses

G. Balakrishnan, A. Zhao, A. V. Dalca, F. Durand, J. Guttag

CVPR 2018 (oral)

paper, code

Video diff: highlighting differences between similar actions in videos

G. Balakrishnan, F. Durand, J. Guttag

Siggraph Asia 2015 (oral)

paper

An Unsupervised Learning Model for Deformable Medical Image Registration

G. Balakrishnan, A. Zhao, M. R. Sabuncu, J. Guttag, A. V. Dalca

CVPR 2018

paper, code

Press:

mit news, nvidia, innovatorsmag, extremetech, semiengineering, physicsworld, electronics360, radiologybusiness, futurelab3d, 

techexplorist, healthimaging, acceleratingbiz, bionengineeringtoday

VoxelMorph: A Learning Framework for Deformable Medical Image Registration

G. Balakrishnan, A. Zhao, M.R. Sabuncu, J. Guttag, A. V. Dalca

IEEE TMI: Transactions in Medical Imaging 2019

paper, code

Data augmentation using learned transforms for one-shot medical image segmentation

A. Zhao, G. Balakrishnan, F. Durand, J. Guttag, A. V. Dalca

CVPR 2019 (oral)

paper, code

Unsupervised Learning of Probabilistic Diffeomorphic Registration 

for Images and Surfaces

A. V. Dalca, G. Balakrishnan, J. Guttag, and M. R. Sabuncu

Medical Image Analysis (MedIA) 2019

paper

Detecting Pulse from Head Motions in Video

G. Balakrishnan, F. Durand, J. Guttag

CVPR 2013

paper, video

Press:

mit news, phys.org, newscientist, cnet, 

fox news, sciencenews, kurzweilai

A Video-Based Method for Objectively Rating Ataxia

R. Jaroensri, A. Zhao, G. Balakrishnan, D. Lo, 

J. Schmahmann, J. Guttag, F. Durand

MLHC 2017

paper

Scalable personalization of long-term physiological monitoring: 

Active learning methodologies for epileptic seizure onset detection

G. Balakrishnan, Z. Syed

AISTATS 2012

paper