
Selfsupervised Dynamic CT Perfusion Image Denoising with Deep Neural Networks
Dynamic computed tomography perfusion (CTP) imaging is a promising appro...
read it

Small indistribution changes in 3D perspective and lighting fool both CNNs and Transformers
Neural networks are susceptible to small transformations including 2D ro...
read it

Cascaded Text Generation with Markov Transformers
The two dominant approaches to neural text generation are fully autoregr...
read it

Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos
Learning to predict scene depth from RGB inputs is a challenging task bo...
read it

Deep learning tools for the measurement of animal behavior in neuroscience
Recent advances in computer vision have made accurate, fast and robust m...
read it

Unsupervised Discovery of Sparse Multimodal Representations in High Dimensional Data
Extracting an understanding of the underlying system from high dimension...
read it

Deep Verifier Networks: Verification of Deep Discriminative Models with Deep Generative Models
AI Safety is a major concern in many deep learning applications such as ...
read it

Learn to Intervene: An Adaptive Learning Policy for Restless Bandits in Application to Preventive Healthcare
In many public health settings, it is important for patients to adhere t...
read it

Designing Environments Conducive to Interpretable Robot Behavior
Designing robots capable of generating interpretable behavior is a prere...
read it

Towards generative adversarial networks as a new paradigm for radiology education
Medical students and radiology trainees typically view thousands of imag...
read it

Subgraph Neural Networks
Deep learning methods for graphs achieve remarkable performance on many ...
read it

Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images
The rapidly emerging field of computational pathology has the potential ...
read it

Unsupervised Instance Segmentation in Microscopy Images via Panoptic Domain Adaptation and Task Reweighting
Unsupervised domain adaptation (UDA) for nuclei instance segmentation is...
read it

Learning to Complement Humans
A rising vision for AI in the open world centers on the development of s...
read it

Direct Reconstruction of Linear Parametric Images from Dynamic PET Using Nonlocal Deep Image Prior
Direct reconstruction methods have been developed to estimate parametric...
read it

Pathomic Fusion: An Integrated Framework for Fusing Histopathology and Genomic Features for Cancer Diagnosis and Prognosis
Cancer diagnosis, prognosis and therapeutic response predictions are bas...
read it

Confidence Calibration and Predictive Uncertainty Estimation for Deep Medical Image Segmentation
Fully convolutional neural networks (FCNs), and in particular UNets, ha...
read it

Neuroscienceinspired online unsupervised learning algorithms
Although the currently popular deep learning networks achieve unpreceden...
read it

Unsupervised Learning of Solutions to Differential Equations with Generative Adversarial Networks
Solutions to differential equations are of significant scientific and en...
read it

Towards a Unified Framework for Fair and Stable Graph Representation Learning
As the representations output by Graph Neural Networks (GNNs) are increa...
read it

Gaussian Process Convolutional Dictionary Learning
Convolutional dictionary learning (CDL), the problem of estimating shift...
read it

A Topological Nomenclature for 3D Shape Analysis in Connectomics
An essential task in nanoscale connectomics is the morphology analysis ...
read it

Emergent Properties of Foveated Perceptual Systems
We introduce foveated perceptual systems, inspired by human biological s...
read it

SemiSupervised Deep Learning for Abnormality Classification in Retinal Images
Supervised deep learning algorithms have enabled significant performance...
read it

Deep Predictive Motion Tracking in Magnetic Resonance Imaging: Application to Fetal Imaging
Fetal magnetic resonance imaging (MRI) is challenged by uncontrollable, ...
read it

Deep Double Descent: Where Bigger Models and More Data Hurt
We show that a variety of modern deep learning tasks exhibit a "doubled...
read it

An Empirical Framework for Domain Generalization in Clinical Settings
Clinical machine learning models experience significantly degraded perfo...
read it

Learning to Prune: Speeding up Repeated Computations
It is common to encounter situations where one must solve a sequence of ...
read it

A Deep Attentive Convolutional Neural Network for Automatic Cortical Plate Segmentation in Fetal MRI
Fetal cortical plate segmentation is essential in quantitative analysis ...
read it

Too many cooks: Coordinating multiagent collaboration through inverse planning
Collaboration requires agents to coordinate their behavior on the fly, s...
read it

Collapsing Bandits and Their Application to Public Health Interventions
We propose and study Collpasing Bandits, a new restless multiarmed band...
read it

TCL: Transformerbased Dynamic Graph Modelling via Contrastive Learning
Dynamic graph modeling has recently attracted much attention due to its ...
read it

Computationally Efficient Cascaded Training for Deep Unrolled Network in CT Imaging
Dose reduction in computed tomography (CT) has been of great research in...
read it

Thwarting Adversarial Examples: An L_0RobustSparse Fourier Transform
We give a new algorithm for approximating the Discrete Fourier transform...
read it

A machine learningbased method for estimating the number and orientations of major fascicles in diffusionweighted magnetic resonance imaging
Multicompartment modeling of diffusionweighted magnetic resonance imag...
read it

What can human minimal videos tell us about dynamic recognition models?
In human vision objects and their parts can be visually recognized from ...
read it

Statistical Inference with MEstimators on Bandit Data
Bandit algorithms are increasingly used in real world sequential decisio...
read it

Fast, Structured Clinical Documentation via Contextual Autocomplete
We present a system that uses a learned autocompletion mechanism to faci...
read it

Can Deep Learning Outperform Modern Commercial CT Image Reconstruction Methods?
Commercial iterative reconstruction techniques on modern CT scanners tar...
read it

Seeing in the dark with recurrent convolutional neural networks
Classical convolutional neural networks (cCNNs) are very good at categor...
read it

MultiTask Ordinal Regression for Jointly Predicting the Trustworthiness and the Leading Political Ideology of News Media
In the context of fake news, bias, and propaganda, we study two importan...
read it

ExpertMatcher: Automating ML Model Selection for Users in Resource Constrained Countries
In this work we introduce ExpertMatcher, a method for automating deep le...
read it

A Learning Strategy for Contrastagnostic MRI Segmentation
We present a deep learning strategy that enables, for the first time, co...
read it

Online Residential Demand Response via Contextual MultiArmed Bandits
Residential load demands have huge potential to be exploited to enhance ...
read it

BanditPAM: Almost Linear Time kMedoids Clustering via MultiArmed Bandits
Clustering is a ubiquitous task in data science. Compared to the commonl...
read it

Fast Physical Activity Suggestions: Efficient Hyperparameter Learning in Mobile Health
Users can be supported to adopt healthy behaviors, such as regular physi...
read it

Deep Neural Networks are Surprisingly Reversible: A Baseline for ZeroShot Inversion
Understanding the behavior and vulnerability of pretrained deep neural ...
read it

Smarter Parking: Using AI to Identify Parking Inefficiencies in Vancouver
Onstreet parking is convenient, but has many disadvantages: onstreet s...
read it

Assessing the validity of saliency maps for abnormality localization in medical imaging
Saliency maps have become a widely used method to assess which areas of ...
read it

SuperBPD: Super BoundarytoPixel Direction for Fast Image Segmentation
Image segmentation is a fundamental vision task and a crucial step for m...
read it
Harvard University
Harvard University is a private Ivy League research university in Cambridge, Massachusetts, with about 6,700 undergraduate students and about 15,250 postgraduate students.