Search Results for author:
Found 30 papers, 15 papers with code
Metric-guided Image Reconstruction Bounds via Conformal Prediction
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.
ElasticDiffusion: Training-free Arbitrary Size Image Generation through Global-Local Content Separation
We propose ElasticDiffusion, a novel training-free decoding method that enables pretrained text-to-image diffusion models to generate images with various sizes.
GELDA: A generative language annotation framework to reveal visual biases in datasets
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.
Improving Denoising Diffusion Probabilistic Models via Exploiting Shared Representations
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.
ISLAND: Informing Brightness and Surface Temperature Through a Land Cover-based Interpolator
Our approach uses thermal infrared images from Landsat 8 (at 30 m resolution with 16-day revisit cycles) and the NLCD land cover dataset.
Benchmarking Algorithmic Bias in Face Recognition: An Experimental Approach Using Synthetic Faces and Human Evaluation
We validate our method quantitatively by evaluating race and gender biases of three research-grade face recognition models.
CT Reconstruction from Few Planar X-rays with Application towards Low-resource Radiotherapy
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.
F?D: On understanding the role of deep feature spaces on face generation evaluation
Moreover, FD using features from a face gender classifier emphasize hair length more than distances in an identity (recognition) feature space.
Visualizing chest X-ray dataset biases using GANs
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.
X-ray Recognition: Patient identification from X-rays using a contrastive objective
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).
MadEye: Boosting Live Video Analytics Accuracy with Adaptive Camera Configurations
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.
SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries
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.
Linking convolutional kernel size to generalization bias in face analysis CNNs
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.
WIRE: Wavelet Implicit Neural Representations
Implicit neural representations (INRs) have recently advanced numerous vision-related areas.
Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers
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
We introduce a new neural signal model designed for efficient high-resolution representation of large-scale signals.
Rayleigh EigenDirections (REDs): GAN latent space traversals for multidimensional features
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
Measuring biases of vision systems with respect to protected attributes like gender and age is critical as these systems gain widespread use in society.
Better Aggregation in Test-Time Augmentation
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.
Towards causal benchmarking of bias in face analysis algorithms
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
We present a probabilistic model that, given a single image of a completed painting, recurrently synthesizes steps of the painting process.
Visual Deprojection: Probabilistic Recovery of Collapsed Dimensions
We introduce visual deprojection: the task of recovering an image or video that has been collapsed along a dimension.
Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces
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
Data augmentation using learned transformations for one-shot medical image segmentation
Image segmentation is an important task in many medical applications.
Ranked #1 on
Brain Image Segmentation
on T1-weighted MRI
VoxelMorph: A Learning Framework for Deformable Medical Image Registration
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
Unsupervised Learning for Fast Probabilistic Diffeomorphic Registration
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
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.
An Unsupervised Learning Model for Deformable Medical Image Registration
We define registration as a parametric function, and optimize its parameters given a set of images from a collection of interest.
A Video-Based Method for Objectively Rating Ataxia
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.
Detecting Pulse from Head Motions in Video
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.
