![KU Leuven](../../KUL%20logo%202_2.png)
Strategie: Statistically Efficient Structured
Prediction for Computer Vision and Medical Imaging
Matthew B. Blaschko
Overview:
This project involves the development of statistical methodologies for
structured prediction and their application to computer vision and
medical image analysis.
This page collects publications, datasets, and other results related to
our research produced with the support of the "Strategie" Marie Curie
Career
Integration Grant with PI Matthew Blaschko.
Personnel:
Publications:
- Belilovsky, E.: Structured
Sparse Learning on Graphs in
High-Dimensional Data with Applications to Neuroimaging.
PhD Thesis,
Université Paris-Saclay & KU Leuven, 2018
- Bounliphone, W.: Statistically
and computationally efficient
hypothesis tests for dependency and similarity.
PhD Thesis,
Université Paris-Saclay & KU Leuven, 2017
- Yu, J.: Empirical
risk minimization with non-modular loss functions.
PhD Thesis,
Université Paris-Saclay, 2017
- Orlando, J. I.: Machine
learning for ophthalmic screening and
diagnostics from fundus images. PhD Thesis, Universidad Nacional del
Centro de la Provincia de Buenos Aires, 2017.
- Rannen Triki, A., M. Berman, and M. B.
Blaschko: Stochastic Weighted Function
Norm Regularization. arXiv:1710.06703, 2017. [bibtex]
- Rannen Triki, A., R. Aljundi, M. B. Blaschko, and
T. Tuytelaars:
Encoder Based Lifelong
Learning. International Conference on Computer Vision (ICCV), 2017.
[bibtex; doi]
- Orlando, J. I., K. van Keer, J. Barbosa Breda, H. L. Manterola, M. B.
Blaschko, and A. Clausse: Proliferative
Diabetic Retinopathy
Characterization based on Fractal Features: Evaluation on a Publicly
Available Data Set. Medical Physics, 44(12):6425-6434, 2017.
[bibtex; code;
doi]
- Blaschko, M. B.: Slack and
Margin Rescaling as Convex Extensions of Supermodular Functions.
International Conference on Energy Minimization Methods in Computer
Vision and Pattern Recognition (EMMCVPR), 2017. [bibtex; code]
- Berman, M. and M. B. Blaschko: Optimization of the Jaccard
index for image segmentation with the Lovász hinge.
arXiv:1705.08790,
2017. [bibtex; code]
- Belilovsky, E.,
K. Kastner, G. Varoquaux, and
M. B. Blaschko: Learning
to Discover Sparse Graphical Models.
International Conference on Machine Learning (ICML),
2017. [bibtex; code;
video]
- Rannen Triki, A.,
M. B. Blaschko,
Y. M. Jung, S.
Song, H. J. Han,
S. I. Kim, C.
Joo: Intraoperative
margin assessment of human breast tissue in optical
coherence tomography images using deep neural networks.
arXiv:1703.10827, 2017. [bibtex; code]
- Belilovsky, E., M. B. Blaschko, J. R. Kiros, R. Urtasun, R. Zemel:
Joint
Embeddings of
Scene Graphs and Images. International Conference on
Learning Representations Workshop Track (ICLR), 2017.
[bibtex]
- Belilovsky, E., K. Kastner, G. Varoquaux, and M. B. Blaschko:
Learning
to Discover Sparse Graphical Models. International Conference on
Learning Representations Workshop Track (ICLR), 2017.
[bibtex; code]
- Yu, J. and M. B.
Blaschko:
An Efficient Decomposition
Framework for Discriminative Segmentation with Supermodular Losses.
arXiv:1702.03690, 2017. [bibtex; code]
- Orlando, J. I., E. Prokofyeva, and M. B. Blaschko: A
Discriminatively Trained Fully Connected Conditional Random Field
Model for Blood Vessel Segmentation in Fundus
Images. IEEE Transactions on Biomedical Engineering, 64(1):16-27,
2017.
[bibtex; code and
data; doi]
- Belilovsky, E., G. Varoquaux, and M. B. Blaschko: Testing
for Differences in Gaussian Graphical Models: Applications to Brain
Connectivity. Neural Information Processing Systems (NIPS), 2016.
[bibtex; code]
- Rannen Triki, A. and M. B. Blaschko: Stochastic
Function Norm
Regularization of DNNs. NIPS Workshop on Optimization for Machine
Learning
(OPT), 2016. [bibtex; code]
- Berman, M. and M. B. Blaschko: Efficient
optimization for probably
submodular constraints in CRFs. NIPS Workshop on Constructive Machine
Learning, 2016. [bibtex; code]
- Rannen Triki, A. and M. B. Blaschko: Stochastic
Function Norm
Regularization of Deep Networks. In Women in Machine Learning
Workshop.
Barcelona, Spain, 2016. [bibtex; code]
- Yu, J. and M. B. Blaschko: Efficient Learning
for Discriminative
Segmentation with Supermodular Losses. In Women in Machine Learning
Workshop. Barcelona, Spain, 2016. [bibtex; code]
- Bounliphone, W., E. Belilovsky, A. Tenenhaus, I.
Antonoglou, A. Gretton, and M. B. Blaschko: Fast Non-Parametric Tests of
Relative
Dependency and Similarity. arXiv:1611.05740, 2016.
[bibtex; code;
code]
- Orlando, J. I., E. Prokofyeva, M. del Fresno, and M. B.
Blaschko: Convolutional
Neural Network Transfer for Automated Glaucoma Identification.
International Symposium on Medical Information Processing and Analysis,
2016. [bibtex;
code;
doi]
- Yu, J. and M. B. Blaschko: Efficient Learning for
Discriminative
Segmentation with Supermodular Losses. British Machine Vision
Conference
(BMVC), 2016. [bibtex; code;
doi]
- Yu, J. and M. B. Blaschko: A
Convex Surrogate Operator for General
Non-Modular Loss Functions. Benelearn. Kortrijk, Belgium, 2016.
[bibtex; code]
- Rannen Triki, A. and M.
B. Blaschko: Stochastic
Function Norm Regularization of Deep Networks.
arXiv:1605.09085,
2016. [bibtex; code]
- Bounliphone, W. and M. B. Blaschko: A U-statistic
Approach to Hypothesis Testing for
Structure Discovery in Undirected Graphical Models. arXiv:1604.01733,
2016. [bibtex; code]
- Ghafarianzadeh, M., M. B. Blaschko, and G. Sibley: Efficient,
Dense, Object-based Segmentation from RGBD Video. IEEE International
Conference on Robotics and Automation (ICRA), 2016.
[bibtex;
doi]
- Yu, J. and M. B. Blaschko: A
Convex
Surrogate Operator
for General Non-Modular Loss Functions. International Conference on
Artificial Intelligence and Statistics (AISTATS), 2016. [bibtex; code]
- Zaremba, W. and M. B. Blaschko: Discriminative
training of CRF models with probably submodular
constraints. IEEE Winter Conference on Applications of Computer Vision
(WACV), 2016. [bibtex; code; doi]
- Bounliphone, W., E. Belilovsky, M. B. Blaschko, I. Antonoglou, and
A. Gretton: A Test of
Relative Similarity for Model Selection in Generative Models.
International Conference on Learning Representations (ICLR), 2016.
[Note: Université Paris-Saclay STIC Doctoral School Best
Scientific Contribution Award; bibtex; code]
- Gkirtzou, K. and M. B. Blaschko: The Pyramid
Quantized Weisfeiler-Lehman Graph Representation. Neurocomputing,
173(3):1495-1507, 2016. [bibtex; code;
doi]
- Sidahmed, H., E. Prokofyeva, and M. B. Blaschko:
Discovering
Predictors of Mental Health Service Utilization with
k-support
Regularized Logistic Regression. Information Sciences, 329:937-949,
2016. [bibtex; code; doi]
- Yu, J. and M. B. Blaschko: The Lovász Hinge:
A Convex Surrogate for Submodular
Losses. arXiv:1512.07797, 2015. [bibtex; code]
- Blaschko, M. B. and J. Yu: Hardness
Results for Structured
Learning and Inference with Multiple Correct Outputs. Constructive
Machine Learning Workshop at ICML, 2015. [bibtex]
- Belilovsky, E., A. Argyriou, G. Varoquaux, and M. B. Blaschko:
Convex
Relaxations of Penalties for Sparse Correlated
Variables With Bounded Total Variation. Machine Learning,
100(2-3):533-553,
2015. [bibtex; code;
doi]
- Yu, J. and M. B. Blaschko: Learning
Submodular Losses with the
Lovász Hinge. International Conference on Machine Learning
(ICML),
2015. [bibtex; code]
- Bounliphone, W., A. Gretton, A. Tenenhaus, and M. B. Blaschko: A
low variance consistent test of relative dependency. International
Conference on Machine Learning (ICML),
2015. [bibtex; code]
- Belilovsky, E., K. Gkirtzou, M. Misyrlis, A. B.
Konova, J. Honorio, N. Alia-Klein, R. Z. Goldstein, D. Samaras,
and M. B. Blaschko: Predictive
sparse modeling of fMRI data for improved
classication, regression, and visualization using the
k-support norm. Computerized Medical Imaging and
Graphics, 46(1):40-46, 2015. [bibtex;
code; doi]
- Belilovsky, E., A. Argyriou, and M. B. Blaschko: Approximating
Combined Discrete Total Variation and Correlated Sparsity With
Convex Relaxations. NIPS Workshop on Discrete and Combinatorial
Problems in Machine Learning, 2014. [bibtex; code]
- Bounliphone, W., A. Gretton, and M. B. Blaschko: Kernel
non-parametric tests of relative dependency. NIPS Workshop on Modern
Nonparametrics 3: Automating the Learning Pipeline, 2014. [bibtex; code]
- Yu, J. and M. B. Blaschko: Lovasz Hinge for Learning
Submodular
Losses. NIPS Workshop on Representation and Learning Methods for
Complex Outputs, 2014. [bibtex; code]
- Blaschko, M. B.: Advances
in Empirical Risk Minimization for Image
Analysis and Pattern Recognition. Mémoire d'habilitation
à diriger des recherches, École Normale
Supérieure de Cachan, 2014. [bibtex]
- Orlando, J. I. and M. B. Blaschko: Learning
fully-connected CRFs
for blood vessel segmentation in
retinal images. Medical Image Computing and Computer Assisted
Intervention (MICCAI),
2014. [bibtex; data;
doi]
- Ghafarianzadeh, M., M. B. Blaschko, and G. Sibley: Unsupervised
Spatio-Temporal Segmentation with
Sparse Spectral-Clustering. British Machine Vision Conference (BMVC),
2014. [bibtex; doi]
- Blaschko, M. B., A. Mittal, and E. Rahtu: An
O(n log n) Cutting
Plane Algorithm for Structured
Output Ranking. 36th German Conference on Pattern Recognition (GCPR),
2014. [bibtex; doi]
- Misyrlis, M., A. B. Konova, M. B. Blaschko, J.
Honorio, N. Alia-Klein, R. Z. Goldstein, D. Samaras: Predicting
cross-task behavioral variables from fMRI data using the k-support
norm. Sparsity Techniques in Medical Imaging,
2014. [Note: Best paper award; bibtex; code]
- Vedaldi, A., S. Mahendran, S. Tsogkas, S. Maji, R. Girshick,
J. Kannala, E. Rahtu, I. Kokkinos, M. B. Blaschko, D. Weiss,
B. Taskar, K. Simonyan, N. Saphra, and S. Mohamed:
Understanding
Objects in Detail with Fine-grained Attributes.
Proceedings of
the IEEE Conference on Computer Vision and Pattern Recognition
(CVPR),
2014. [bibtex; code; data;
doi]
- Blaschko,
M. B.: Machine
Learning
for Neurological Disorders. Centraliens, 632 (2014)
40-42. [bibtex]
Acknowledgements:
We acknowledge support from Marie
Skłodowska-Curie actions through project number FP7-MC-CIG
334380.