
Efficient Object Detection in Large Images using Deep Reinforcement Learning
Traditionally, an object detector is applied to every part of the scene ...
read it

Stable Prediction with Model Misspecification and Agnostic Distribution Shift
For many machine learning algorithms, two main assumptions are required ...
read it

PyTorch: An Imperative Style, HighPerformance Deep Learning Library
Deep learning frameworks have often focused on either usability or speed...
read it

Regression Planning Networks
Recent learningtoplan methods have shown promising results on planning...
read it

An Application of Generative Adversarial Networks for Super Resolution Medical Imaging
Acquiring High Resolution (HR) Magnetic Resonance (MR) images requires t...
read it

DermGAN: Synthetic Generation of Clinical Skin Images with Pathology
Despite the recent success in applying supervised deep learning to medic...
read it

Large Batch Simulation for Deep Reinforcement Learning
We accelerate deep reinforcement learningbased training in visually com...
read it

Evaluating the Disentanglement of Deep Generative Models through Manifold Topology
Learning disentangled representations is regarded as a fundamental task ...
read it

Computational model discovery with reinforcement learning
The motivation of this study is to leverage recent breakthroughs in arti...
read it

Deep Bayesian Active Learning for Multiple Correct Outputs
Typical active learning strategies are designed for tasks, such as class...
read it

Local Linear Forests
Random forests are a powerful method for nonparametric regression, but ...
read it

4D SpatioTemporal ConvNets: Minkowski Convolutional Neural Networks
In many robotics and VR/AR applications, 3Dvideos are readilyavailable...
read it

Learning by Abstraction: The Neural State Machine
We introduce the Neural State Machine, seeking to bridge the gap between...
read it

Learning Reward Functions from Diverse Sources of Human Feedback: Optimally Integrating Demonstrations and Preferences
Reward functions are a common way to specify the objective of a robot. A...
read it

TransGaGa: GeometryAware Unsupervised ImagetoImage Translation
Unsupervised imagetoimage translation aims at learning a mapping betwe...
read it

cFineGAN: Unsupervised multiconditional finegrained image generation
We propose an unsupervised multiconditional image generation pipeline: ...
read it

Adversarial Representation Active Learning
Active learning aims to develop labelefficient algorithms by querying t...
read it

Predicting Regression Probability Distributions with Imperfect Data Through Optimal Transformations
The goal of regression analysis is to predict the value of a numeric out...
read it

A Meanfield Analysis of Deep ResNet and Beyond: Towards Provable Optimization Via Overparameterization From Depth
Training deep neural networks with stochastic gradient descent (SGD) can...
read it

MetaReinforcement Learning Robust to Distributional Shift via Model Identification and Experience Relabeling
Reinforcement learning algorithms can acquire policies for complex tasks...
read it

Automating Interpretability: Discovering and Testing Visual Concepts Learned by Neural Networks
Interpretability has become an important topic of research as more machi...
read it

ImagineNet: Restyling Apps Using Neural Style Transfer
This paper presents ImagineNet, a tool that uses a novel neural style tr...
read it

Hierarchical Reinforcement Learning with AdvantageBased Auxiliary Rewards
Hierarchical Reinforcement Learning (HRL) is a promising approach to sol...
read it

Action Genome: Actions as Composition of Spatiotemporal Scene Graphs
Action recognition has typically treated actions and activities as monol...
read it

Neural Network Generalization: The impact of camera parameters
We quantify the generalization of a convolutional neural network (CNN) t...
read it

Roundtrip: A Deep Generative Neural Density Estimator
Density estimation is a fundamental problem in both statistics and machi...
read it

Visual Relationships as Functions: Enabling FewShot Scene Graph Prediction
Scene graph prediction  classifying the set of objects and predicates...
read it

Compositional Explanations of Neurons
We describe a procedure for explaining neurons in deep representations b...
read it

Generative 3D Part Assembly via Dynamic Graph Learning
Autonomous part assembly is a challenging yet crucial task in 3D compute...
read it

Convex Hierarchical Clustering for GraphStructured Data
Convex clustering is a recent stable alternative to hierarchical cluster...
read it

Automatically Neutralizing Subjective Bias in Text
Texts like news, encyclopedias, and some social media strive for objecti...
read it

Separating the Effects of Batch Normalization on CNN Training Speed and Stability Using Classical Adaptive Filter Theory
Batch Normalization (BatchNorm) is commonly used in Convolutional Neural...
read it

Sufficient Representations for Categorical Variables
Many learning algorithms require categorical data to be transformed into...
read it

Pretraining Graph Neural Networks
Many applications of machine learning in science and medicine, including...
read it

Asking Easy Questions: A UserFriendly Approach to Active Reward Learning
Robots can learn the right reward function by querying a human expert. E...
read it

Question Type Classification Methods Comparison
The paper presents a comparative study of stateoftheart approaches fo...
read it

Design Space for Graph Neural Networks
The rapid evolution of Graph Neural Networks (GNNs) has led to a growing...
read it

Online Model Distillation for Efficient Video Inference
Highquality computer vision models typically address the problem of und...
read it

MultiAgent Deep Reinforcement Learning for Largescale Traffic Signal Control
Reinforcement learning (RL) is a promising datadriven approach for adap...
read it

AirSim Drone Racing Lab
Autonomous drone racing is a challenging research problem at the interse...
read it

Imitation Learning for Human Pose Prediction
Modeling and prediction of human motion dynamics has long been a challen...
read it

Datadependent Sample Complexity of Deep Neural Networks via Lipschitz Augmentation
Existing Rademacher complexity bounds for neural networks rely only on n...
read it

Deep Reinforcement Learning for Constrained Field Development Optimization in Subsurface Twophase Flow
We present a deep reinforcement learningbased artificial intelligence a...
read it

Accelerating cardiac cine MRI beyond compressed sensing using DLESPIRiT
A novel neural network architecture, known as DLESPIRiT, is proposed to...
read it

MetaLearning without Memorization
The ability to learn new concepts with small amounts of data is a critic...
read it

Deep Optics for Monocular Depth Estimation and 3D Object Detection
Depth estimation and 3D object detection are critical for scene understa...
read it

Playing Go without Game Tree Search Using Convolutional Neural Networks
The game of Go has a long history in East Asian countries, but the field...
read it

SelfSupervised Learning of State Estimation for Manipulating Deformable Linear Objects
We demonstrate modelbased, visual robot manipulation of linear deformab...
read it

Predicting the Physical Dynamics of Unseen 3D Objects
Machines that can predict the effect of physical interactions on the dyn...
read it

A Delay Metric for Video Object Detection: What Average Precision Fails to Tell
Average precision (AP) is a widely used metric to evaluate detection acc...
read it
Stanford University
Stanford University, one of the world's leading teaching and research universities, is dedicated to finding solutions to big challenges and to preparing students for leadership in a complex world.