1 code implementation • 23 Apr 2024 • Matt Y Cheung, Tucker J Netherton, Laurence E Court, Ashok Veeraraghavan, Guha Balakrishnan
We apply our method to sparse-view CT for downstream radiotherapy planning and show 1) that metric-guided bounds have valid coverage for downstream metrics while conventional pixel-wise bounds do not and 2) anatomical differences of upper/lower bounds between metric-guided and pixel-wise methods.
1 code implementation • 30 Nov 2023 • Moayed Haji-Ali, Guha Balakrishnan, Vicente Ordonez
We propose ElasticDiffusion, a novel training-free decoding method that enables pretrained text-to-image diffusion models to generate images with various sizes.
no code implementations • 29 Nov 2023 • Krish Kabra, Kathleen M. Lewis, Guha Balakrishnan
Results on real datasets show that GELDA can generate accurate and diverse visual attribute suggestions, and uncover biases such as confounding between class labels and background features.
no code implementations • 27 Nov 2023 • Delaram Pirhayatifard, Mohammad Taha Toghani, Guha Balakrishnan, César A. Uribe
In this work, we address the challenge of multi-task image generation with limited data for denoising diffusion probabilistic models (DDPM), a class of generative models that produce high-quality images by reversing a noisy diffusion process.
no code implementations • 21 Sep 2023 • Yuhao Liu, Pranavesh Panakkal, Sylvia Dee, Guha Balakrishnan, Jamie Padgett, Ashok Veeraraghavan
Our approach uses thermal infrared images from Landsat 8 (at 30 m resolution with 16-day revisit cycles) and the NLCD land cover dataset.
no code implementations • ICCV 2023 • Hao Liang, Pietro Perona, Guha Balakrishnan
We validate our method quantitatively by evaluating race and gender biases of three research-grade face recognition models.
1 code implementation • 4 Aug 2023 • Yiran Sun, Tucker Netherton, Laurence Court, Ashok Veeraraghavan, Guha Balakrishnan
In this work, we propose a method to generate CT volumes from few (<5) planar X-ray observations using a prior data distribution, and perform the first evaluation of such a reconstruction algorithm for a clinical application: radiotherapy planning.
no code implementations • 31 May 2023 • Krish Kabra, Guha Balakrishnan
Moreover, FD using features from a face gender classifier emphasize hair length more than distances in an identity (recognition) feature space.
no code implementations • 29 Apr 2023 • Hao Liang, Kevin Ni, Guha Balakrishnan
Recent research demonstrates that deep learning models are capable of precisely extracting bio-information (e. g. race, gender and age) from patients' Chest X-Rays (CXRs).
no code implementations • 29 Apr 2023 • Hao Liang, Kevin Ni, Guha Balakrishnan
Recent work demonstrates that images from various chest X-ray datasets contain visual features that are strongly correlated with protected demographic attributes like race and gender.
no code implementations • 4 Apr 2023 • Mike Wong, Murali Ramanujam, Guha Balakrishnan, Ravi Netravali
Camera orientations (i. e., rotation and zoom) govern the content that a camera captures in a given scene, which in turn heavily influences the accuracy of live video analytics pipelines.
1 code implementation • CVPR 2023 • Ahmed Imtiaz Humayun, Randall Balestriero, Guha Balakrishnan, Richard Baraniuk
In this paper, we go one step further by developing the first provably exact method for computing the geometry of a DN's mapping - including its decision boundary - over a specified region of the data space.
no code implementations • 7 Feb 2023 • Hao Liang, Josue Ortega Caro, Vikram Maheshri, Ankit B. Patel, Guha Balakrishnan
Our framework is experimental, in that we train several versions of a network with an intervention to a specific hyperparameter, and measure the resulting causal effect of this choice on performance bias when a particular out-of-distribution image perturbation is applied.
2 code implementations • CVPR 2023 • Vishwanath Saragadam, Daniel LeJeune, Jasper Tan, Guha Balakrishnan, Ashok Veeraraghavan, Richard G. Baraniuk
Implicit neural representations (INRs) have recently advanced numerous vision-related areas.
no code implementations • CVPR 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.
1 code implementation • 7 Feb 2022 • Vishwanath Saragadam, Jasper Tan, Guha Balakrishnan, Richard G. Baraniuk, Ashok Veeraraghavan
We introduce a new neural signal model designed for efficient high-resolution representation of large-scale signals.
no code implementations • 25 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.
1 code implementation • 24 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.
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.
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.
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.
no code implementations • ICCV 2019 • Guha Balakrishnan, Adrian V. Dalca, Amy Zhao, John V. Guttag, Fredo Durand, William T. Freeman
We introduce visual deprojection: the task of recovering an image or video that has been collapsed along a dimension.
1 code implementation • 8 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).
Ranked #2 on Diffeomorphic Medical Image Registration on OASIS+ADIBE+ADHD200+MCIC+PPMI+HABS+HarvardGSP
Constrained Diffeomorphic Image Registration Deformable Medical Image Registration +2
2 code implementations • CVPR 2019 • Amy Zhao, Guha Balakrishnan, Frédo Durand, John V. Guttag, Adrian V. Dalca
Image segmentation is an important task in many medical applications.
Ranked #1 on Brain Image Segmentation on T1-weighted MRI
7 code implementations • 14 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.
Ranked #1 on Diffeomorphic Medical Image Registration on OASIS+ADIBE+ADHD200+MCIC+PPMI+HABS+HarvardGSP (Dice metric)
Deformable Medical Image Registration Diffeomorphic Medical Image Registration +1
2 code implementations • 11 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.
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.
3 code implementations • CVPR 2018 • Guha Balakrishnan, Amy Zhao, Mert R. Sabuncu, John Guttag, Adrian V. Dalca
We define registration as a parametric function, and optimize its parameters given a set of images from a collection of interest.
no code implementations • 13 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.
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.