Search Results for author: Samuel Madden

Found 11 papers, 4 papers with code

RoadTagger: Robust Road Attribute Inference with Graph Neural Networks

1 code implementation28 Dec 2019 Songtao He, Favyen Bastani, Satvat Jagwani, Edward Park, Sofiane Abbar, Mohammad Alizadeh, Hari Balakrishnan, Sanjay Chawla, Samuel Madden, Mohammad Amin Sadeghi

The usage of graph neural networks allows information propagation on the road network graph and eliminates the receptive field limitation of image classifiers.

Context-Aware Object Detection With Convolutional Neural Networks

no code implementations25 Sep 2019 Yizhou Yan, Lei Cao, Samuel Madden, Elke Rundensteiner

Although the state-of-the-art object detection methods are successful in detecting and classifying objects by leveraging deep convolutional neural networks (CNNs), these methods overlook the semantic context which implies the probabilities that different classes of objects occur jointly.

Object Detection

Unknown-Aware Deep Neural Network

no code implementations25 Sep 2019 Lei Cao, Yizhou Yan, Samuel Madden, Elke Rundensteiner

Unfortunately, although the strong generalization ability of existing CNNs ensures their accuracy when classifying known objects, it also causes them to often assign an unknown to a target class with high confidence.

Image Classification

Deductive Optimization of Relational Data Storage

1 code implementation8 Mar 2019 John K. Feser, Samuel Madden, Nan Tang, Armando Solar-Lezama

Optimizing the physical data storage and retrieval of data are two key database management problems.

Programming Languages Databases

Smallify: Learning Network Size while Training

no code implementations10 Jun 2018 Guillaume Leclerc, Manasi Vartak, Raul Castro Fernandez, Tim Kraska, Samuel Madden

As neural networks become widely deployed in different applications and on different hardware, it has become increasingly important to optimize inference time and model size along with model accuracy.

Active Learning for Crowd-Sourced Databases

no code implementations17 Sep 2012 Barzan Mozafari, Purnamrita Sarkar, Michael J. Franklin, Michael. I. Jordan, Samuel Madden

Based on this observation, we present two new active learning algorithms to combine humans and algorithms together in a crowd-sourced database.

Active Learning

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