Search Results for author: Matthew Blaschko

Found 23 papers, 14 papers with code

Predicting Physical World Destinations for Commands Given to Self-Driving Cars

no code implementations10 Dec 2021 Dusan Grujicic, Thierry Deruyttere, Marie-Francine Moens, Matthew Blaschko

However, surveys have shown that giving more control to an AI in self-driving cars is accompanied by a degree of uneasiness by passengers.

Self-Driving Cars

Differentially Private SGD with Sparse Gradients

no code implementations1 Dec 2021 Junyi Zhu, Matthew Blaschko

To protect sensitive training data, differentially private stochastic gradient descent (DP-SGD) has been adopted in deep learning to provide rigorously defined privacy.

Federated Learning

Learning to ground medical text in a 3D human atlas

1 code implementation CONLL 2020 Dusan Grujicic, Gorjan Radevski, Tinne Tuytelaars, Matthew Blaschko

In this paper, we develop a method for grounding medical text into a physically meaningful and interpretable space corresponding to a human atlas.

Phrase Grounding Visual Grounding

R-GAP: Recursive Gradient Attack on Privacy

2 code implementations ICLR 2021 Junyi Zhu, Matthew Blaschko

However, recent optimization-based gradient attacks show that raw data can often be accurately recovered from gradients.

Federated Learning

Self-supervised context-aware COVID-19 document exploration through atlas grounding

1 code implementation ACL 2020 Dusan Grujicic, Gorjan Radevski, Tinne Tuytelaars, Matthew Blaschko

In this paper, we aim to develop a self-supervised grounding of Covid-related medical text based on the actual spatial relationships between the referred anatomical concepts.

Semixup: In- and Out-of-Manifold Regularization for Deep Semi-Supervised Knee Osteoarthritis Severity Grading from Plain Radiographs

1 code implementation Preprint on arXiv 2020 Huy Hoang Nguyen, Simo Saarakkala, Matthew Blaschko, Aleksei Tiulpin

Finally, when compared to a well-tuned fully supervised baseline that yielded a balanced accuracy (BA) of $70. 9\pm0. 8%$ on the test set, Semixup had comparable performance -- BA of $71\pm0. 8%$ $(p=0. 368)$ while requiring $6$ times less labeled data.

Optimizing the Dice Score and Jaccard Index for Medical Image Segmentation: Theory & Practice

1 code implementation5 Nov 2019 Jeroen Bertels, Tom Eelbode, Maxim Berman, Dirk Vandermeulen, Frederik Maes, Raf Bisschops, Matthew Blaschko

First, we investigate the theoretical differences in a risk minimization framework and question the existence of a weighted cross-entropy loss with weights theoretically optimized to surrogate Dice or Jaccard.

Medical Image Segmentation Semantic Segmentation

Generating superpixels using deep image representations

no code implementations11 Mar 2019 Thomas Verelst, Matthew Blaschko, Maxim Berman

Superpixel algorithms are a common pre-processing step for computer vision algorithms such as segmentation, object tracking and localization.

General Classification Object Tracking +2

Scattering Networks for Hybrid Representation Learning

1 code implementation17 Sep 2018 Edouard Oyallon, Sergey Zagoruyko, Gabriel Huang, Nikos Komodakis, Simon Lacoste-Julien, Matthew Blaschko, Eugene Belilovsky

In particular, by working in scattering space, we achieve competitive results both for supervised and unsupervised learning tasks, while making progress towards constructing more interpretable CNNs.

Representation Learning

Learning to Discover Sparse Graphical Models

1 code implementation ICML 2017 Eugene Belilovsky, Kyle Kastner, Gaël Varoquaux, Matthew Blaschko

Learning this function brings two benefits: it implicitly models the desired structure or sparsity properties to form suitable priors, and it can be tailored to the specific problem of edge structure discovery, rather than maximizing data likelihood.

A Convex Surrogate Operator for General Non-Modular Loss Functions

1 code implementation12 Apr 2016 Jiaqian Yu, Matthew Blaschko

This convex surro-gate is based on a submodular-supermodular decomposition for which the existence and uniqueness is proven in this paper.

A U-statistic Approach to Hypothesis Testing for Structure Discovery in Undirected Graphical Models

1 code implementation6 Apr 2016 Wacha Bounliphone, Matthew Blaschko

For some class of probability distributions, an edge between two variables is present if and only if the corresponding entry in the precision matrix is non-zero.

Two-sample testing

The Lovász Hinge: A Novel Convex Surrogate for Submodular Losses

2 code implementations24 Dec 2015 Jiaqian Yu, Matthew Blaschko

The main tools for constructing convex surrogate loss functions for set prediction are margin rescaling and slack rescaling.

A low variance consistent test of relative dependency

1 code implementation15 Jun 2014 Wacha Bounliphone, Arthur Gretton, Arthur Tenenhaus, Matthew Blaschko

Such a test enables us to determine whether one source variable is significantly more dependent on a first target variable or a second.

B-test: A Non-parametric, Low Variance Kernel Two-sample Test

no code implementations NeurIPS 2013 Wojciech Zaremba, Arthur Gretton, Matthew Blaschko

We propose a family of maximum mean discrepancy (MMD) kernel two-sample tests that have low sample complexity and are consistent.

B-tests: Low Variance Kernel Two-Sample Tests

1 code implementation8 Jul 2013 Wojciech Zaremba, Arthur Gretton, Matthew Blaschko

A family of maximum mean discrepancy (MMD) kernel two-sample tests is introduced.

Two-sample testing

Fine-Grained Visual Classification of Aircraft

1 code implementation21 Jun 2013 Subhransu Maji, Esa Rahtu, Juho Kannala, Matthew Blaschko, Andrea Vedaldi

This paper introduces FGVC-Aircraft, a new dataset containing 10, 000 images of aircraft spanning 100 aircraft models, organised in a three-level hierarchy.

Classification Fine-Grained Image Classification +1

A Note on k-support Norm Regularized Risk Minimization

1 code implementation26 Mar 2013 Matthew Blaschko

The k-support norm has been recently introduced to perform correlated sparsity regularization.

Perceptron Learning of SAT

no code implementations NeurIPS 2012 Alex Flint, Matthew Blaschko

Provided this mapping is based on polynomial time computable statistics of a sentence, we show that the existance of a margin between these data points implies the existance of a polynomial time solver for that SAT subset based on the Davis-Putnam-Logemann-Loveland algorithm.

Simultaneous Object Detection and Ranking with Weak Supervision

no code implementations NeurIPS 2010 Matthew Blaschko, Andrea Vedaldi, Andrew Zisserman

A standard approach to learning object category detectors is to provide strong supervision in the form of a region of interest (ROI) specifying each instance of the object in the training images.

Object Detection Pedestrian Detection

Augmenting Feature-driven fMRI Analyses: Semi-supervised learning and resting state activity

no code implementations NeurIPS 2009 Andreas Bartels, Matthew Blaschko, Jacquelyn A. Shelton

Resting state activity is brain activation that arises in the absence of any task, and is usually measured in awake subjects during prolonged fMRI scanning sessions where the only instruction given is to close the eyes and do nothing.

Learning Taxonomies by Dependence Maximization

no code implementations NeurIPS 2008 Matthew Blaschko, Arthur Gretton

We introduce a family of unsupervised algorithms, numerical taxonomy clustering, to simultaneously cluster data, and to learn a taxonomy that encodes the relationship between the clusters.

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