I am a postdoc at INRIA working with the WILLOW project-team which is part of the Computer Science Department of École Normale Supérieure in Paris.

I did both my undergrad and PhD studies in Moscow, Russia at the Lomonosov Moscow State University (MSU), department of Computational Mathematics and Cybernetics (CMC). At MSU, I worked with Bayesian Methods research group under supervision of Dmitry Vetrov. Between 2012 and 2014, I was an assistant at the department of mathematical methods of prediction and taught several courses to undergrad students. I also gave seminars at Yandex School of Data Analysis. In 2014, I successfully defended my PhD thesis and departed to France to work with Simon Lacoste-Julien and Francis Bach as a member of the SIERRA project-team (machine learning). In 2016, I moved next door to the WILLOW project-team (computer vision) to work with Ivan Laptev.

Selected publications

Work in progress

SEARNN: Training RNNs with Global-Local Losses
Rémi Leblond, Jean-Baptiste Alayrac, Anton Osokin, Simon Lacoste-Julien
On Structured Prediction Theory with Calibrated Convex Surrogate Losses
Anton Osokin, Francis Bach, Simon Lacoste-Julien

Journal papers

Submodular relaxation for inference in Markov random fields
Anton Osokin and Dmitry Vetrov
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 37(7): 1347-1359, 2015
Fast Approximate Energy Minimization with Label Costs
Andrew Delong*, Anton Osokin*, Hossam Isack, Yuri Boykov
*equal contribution
International Journal of Computer Vision (IJCV), 96(1):1-27, 2012

Conference papers

Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs
Anton Osokin*, Jean-Baptiste Alayrac*, Isabella Lukasewitz, Puneet K. Dokania, and Simon Lacoste-Julien
*equal contribution
In proceedings of the International Conference on Machine Learning (ICML), 2016
Breaking Sticks and Ambiguities with Adaptive Skip-gram
Sergey Bartunov, Dmitry Kondrashkin, Anton Osokin, and Dmitry Vetrov
In proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2016
Context-aware CNNs for person head detection
Tuan-Hung Vu, Anton Osokin, and Ivan Laptev
In proceedings of the International Conference on Computer Vision (ICCV), 2015
Tensorizing Neural Networks
Alexander Novikov, Dmitry Podoprikhin, Anton Osokin, and Dmitry Vetrov
Advances in Neural Information Processing Systems (NIPS), 2015
Perceptually Inspired Layout-aware Losses for Image Segmentation
Anton Osokin and Pushmeet Kohli
In proceedings of the European Conference on Computer Vision (ECCV), 2014
Putting MRFs on a Tensor Train
Alexander Novikov, Anton Rodomanov, Anton Osokin, and Dmitry Vetrov
In proceedings of the International Conference on Machine Learning (ICML), 2014
A Principled Deep Random Field Model for Image Segmentation
Pushmeet Kohli, Anton Osokin, and Stefanie Jegelka
In proceedings of the Computer Vision and Pattern Recognition (CVPR), 2013
Minimizing Sparse High-Order Energies by Submodular Vertex-Cover
Andrew Delong, Olga Veksler, Anton Osokin, and Yuri Boykov
Advances in Neural Information Processing Systems (NIPS), 2012
Submodular Decomposition Framework for Inference in Associative Markov Networks with Global Constraints
Anton Osokin, Dmitry Vetrov, and Vladimir Kolmogorov
In proceedings of the Computer Vision and Pattern Recognition (CVPR), 2011
Fast Approximate Energy Minimization with Label Costs
Andrew Delong*, Anton Osokin*, Hossam Isack, and Yuri Boykov
*equal contribution
In proceedings of the Computer Vision and Pattern Recognition (CVPR), 2010

PhD thesis

Submodular relaxation for energy minimization in Markov random fields
Anton Osokin
Lomonosov Moscow State University. 2014. In Russian

Code

ICML 2016 on Frank-Wolfe for SSVM [GitHub]
ICCV 2015 on head detection with CNNs [GitHub]
MATLAB wrapper for cropping images on a GPU [ GitHub]
Submodular Relaxation project (TPAMI 2015, PhD thesis, CVPR 2011) [GitHub]
ECCV 2014 paper on high-order losses [GitHub]
CVPR 2013 paper on cooperative cuts [GitHub]
MATLAB wrapper for TRW-S and LBP algorithms implemented by V. Kolmogorov [GitHub]
MATLAB wrapper for Boykov-Kolmogorov max-flow/min-cut algorithm [GitHub]
MATLAB wrapper for Boykov-Kolmogorov max-flow/min-cut algorithm supporting the dynamic cuts [GitHub]
MATLAB wrapper for IBFS max-flow/min-cut algorithm (this code may be faster than BK in certain cases) [GitHub]
MATLAB wrapper for BK max-flow/min-cut algorithm with options of efficiently computing min-marginals [GitHub]
MATLAB wrapper for QPBO energy minimization algorithm (implementation by V. Kolmogorov) [GitHub]
MATLAB wrapper for Kovtun's energy minimization algorithm (implementation by K. Alahari). This code allows to compute partially optimal solutions for multilabels pairwise Potts MRFs [GitHub]

Teaching

Introduction to discrete optimization at CentraleSupélec, Châtenay-Malabry, France. Co-lecturer with Karteek Alahari. [webpage]
2016
Graphical models at CMC MSU. Seminars and practical sessions. Lecturers: Dmitry Vetrov, Dmitry Kropotov.
2012, 2013, 2014
Graphical models at Yandex Data Analysis School. Seminars and practical sessions. Lecturers: Victor Lempitsky, Dmitry Vetrov.
2011, 2012, 2013
Machine Learning at CMC MSU. Practical sessions.
2012, 2013, 2014
Scientific seminar on Bayesian methods of machine learning at CMC MSU. Co-organizer together with Dmitry Vetrov and Dmitry Kropotov.
2010-2014