Search Results for author: Guha Balakrishnan

Found 16 papers, 10 papers with code

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

no code implementations9 Mar 2022 Dominik Zietlow, Michael Lohaus, Guha Balakrishnan, Matthäus Kleindessner, Francesco Locatello, Bernhard Schölkopf, Chris Russell

Algorithmic fairness is frequently motivated in terms of a trade-off in which overall performance is decreased so as to improve performance on disadvantaged groups where the algorithm would otherwise be less accurate.


MINER: Multiscale Implicit Neural Representations

1 code implementation7 Feb 2022 Vishwanath Saragadam, Jasper Tan, Guha Balakrishnan, Richard G. Baraniuk, Ashok Veeraraghavan

We introduce a new neural signal representation designed for the efficient high-resolution representation of large-scale signals.

Image Reconstruction

Rayleigh EigenDirections (REDs): GAN latent space traversals for multidimensional features

no code implementations25 Jan 2022 Guha Balakrishnan, Raghudeep Gadde, Aleix Martinez, Pietro Perona

We present a method for finding paths in a deep generative model's latent space that can maximally vary one set of image features while holding others constant.

Matched sample selection with GANs for mitigating attribute confounding

1 code implementation24 Mar 2021 Chandan Singh, Guha Balakrishnan, Pietro Perona

Measuring biases of vision systems with respect to protected attributes like gender and age is critical as these systems gain widespread use in society.

Face Generation Gender Bias Detection +1

Better Aggregation in Test-Time Augmentation

no code implementations ICCV 2021 Divya Shanmugam, Davis Blalock, Guha Balakrishnan, John Guttag

In this paper, we present 1) experimental analyses that shed light on cases in which the simple average is suboptimal and 2) a method to address these shortcomings.

Image Classification

Towards causal benchmarking of bias in face analysis algorithms

1 code implementation ECCV 2020 Guha Balakrishnan, Yuanjun Xiong, Wei Xia, Pietro Perona

To address this problem we develop an experimental method for measuring algorithmic bias of face analysis algorithms, which manipulates directly the attributes of interest, e. g., gender and skin tone, in order to reveal causal links between attribute variation and performance change.


Painting Many Pasts: Synthesizing Time Lapse Videos of Paintings

1 code implementation CVPR 2020 Amy Zhao, Guha Balakrishnan, Kathleen M. Lewis, Frédo Durand, John V. Guttag, Adrian V. Dalca

We present a probabilistic model that, given a single image of a completed painting, recurrently synthesizes steps of the painting process.

Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces

1 code implementation8 Mar 2019 Adrian V. Dalca, Guha Balakrishnan, John Guttag, Mert R. Sabuncu

We present a probabilistic generative model and derive an unsupervised learning-based inference algorithm that uses insights from classical registration methods and makes use of recent developments in convolutional neural networks (CNNs).

Constrained Diffeomorphic Image Registration Deformable Medical Image Registration +2

VoxelMorph: A Learning Framework for Deformable Medical Image Registration

6 code implementations14 Sep 2018 Guha Balakrishnan, Amy Zhao, Mert R. Sabuncu, John Guttag, Adrian V. Dalca

In contrast to this approach, and building on recent learning-based methods, we formulate registration as a function that maps an input image pair to a deformation field that aligns these images.

Deformable Medical Image Registration Diffeomorphic Medical Image Registration +1

Unsupervised Learning for Fast Probabilistic Diffeomorphic Registration

2 code implementations11 May 2018 Adrian V. Dalca, Guha Balakrishnan, John Guttag, Mert R. Sabuncu

We demonstrate our method on a 3D brain registration task, and provide an empirical analysis of the algorithm.

Synthesizing Images of Humans in Unseen Poses

1 code implementation CVPR 2018 Guha Balakrishnan, Amy Zhao, Adrian V. Dalca, Fredo Durand, John Guttag

Given an image of a person and a desired pose, we produce a depiction of that person in that pose, retaining the appearance of both the person and background.

Image Generation

A Video-Based Method for Objectively Rating Ataxia

no code implementations13 Dec 2016 Ronnachai Jaroensri, Amy Zhao, Guha Balakrishnan, Derek Lo, Jeremy Schmahmann, John Guttag, Fredo Durand

The performance of our system is comparable to that of a group of ataxia specialists in terms of mean error and correlation, and our system's predictions were consistently within the range of inter-rater variability.

Optical Flow Estimation Pose Estimation

Detecting Pulse from Head Motions in Video

no code implementations CVPR 2013 Guha Balakrishnan, Fredo Durand, John Guttag

We extract heart rate and beat lengths from videos by measuring subtle head motion caused by the Newtonian reaction to the influx of blood at each beat.

Heart Rate Variability

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