This web page is no longer updated. Please, visit my new webpage
|PhD in mathematics (к.ф.-м.н.)
postdoc with INRIA-SIERRA project-team, Paris
E-mail: lastname -at- bayesgroup.ru
I did both my undergrad and PhD studies at the Lomonosov Moscow State University (MSU), faculty of
Computational Mathematics and Cybernetics (CMC). Am the MSU I worked with Bayesian Methods research group under supervision of Dmitry Vetrov. Between 2012 and 2014 I worked as an assistant of the department of mathematical methods of forecasting and taught several courses to undergrad students.
- Machine learning
- Graphical models
- Computer vision
- Anton Osokin, Dmitry Vetrov. Submodular relaxation for inference in Markov random fields. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). Accepted. 2014. pdf + supplementary, code
- Anton Osokin, Pushmeet Kohli. Perceptually Inspired Layout-aware Losses for Image Segmentation. In European Conference on Computer Vision (ECCV), 2014. pdf
- Anton Osokin. PhD thesis: Submodular relaxation for energy minimization in Markov random fields, supervisor: Dmitry Vetrov (Lomonosov Moscow State University), May 2014. In Russian. text (pdf), synopsis (pdf), see TPAMI 2015 paper for the English version
- Alexander Novikov, Anton Rodomanov, Anton Osokin, Dmitry Vetrov. Putting MRFs on a Tensor Train. In International Conference on Machine Learning (ICML), 2014. JMLR: W&CP volume 32. pdf, supplementary, poster, slides, code
- Pushmeet Kohli, Anton Osokin, and Stefanie Jegelka. A Principled Deep Random Field Model for Image Segmentation. In Computer Vision and Pattern Recognition (CVPR), 2013. pdf, supplementary, code
- Andrew Delong, Olga Veksler, Anton Osokin, and Yuri Boykov. Minimizing Sparse High-Order Energies by Submodular Vertex-Cover. Advances in Neural Information Processing Systems (NIPS), 2012. pdf
- Anton Osokin, Dmitry Vetrov. Submodular Relaxation for MRFs with High-Order Potentials. HiPot: ECCV 2012 Workshop on Higher-Order Models and Global Constraints in Computer Vision, 2012. pdf + supplementary
- Andrew Delong, Anton Osokin, Hossam Isack, and Yuri Boykov. Fast Approximate Energy Minimization with Label Costs, International Journal of Computer Vision (IJCV), 96(1):1–27, January 2012. pdf, code
- Dmitry Vetrov, Anton Osokin. Graph Preserving Label Decomposition in Discrete MRFs with Selfish Potentials. In proceedings of International Workshop on Discrete Optimization in Machine learning (DISCML NIPS), December 2011. pdf
- Anton Osokin, Dmitry Vetrov, and Vladimir Kolmogorov. Submodular Decomposition Framework for Inference in Associative Markov Networks with Global Constraints, In Computer Vision and Pattern Recognition (CVPR), June 2011. pdf, code
- Andrew Delong, Anton Osokin, Hossam Isack, and Yuri Boykov. Fast Approximate Energy Minimization with Label Costs,
In Computer Vision and Pattern Recognition (CVPR), June 2010. pdf, code
- Code of Submodular Relaxation project (TPAMI 2015, PhD thesis, ECCV HiPot 2012, DISCML NIPS 2011, CVPR 2011): github
- Code of CVPR 2013 paper on cooperative cuts: coopCuts_CVPR2013_v0.4.zip
- Matlab wrapper for TRW-S and LBP algorithms by V.Kolmogorov: mrfMinimizerMex_trws_lbp.zip
- 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: computeMinMarginals.zip
- 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. partialOptimality_Kovtun.zip
- Seminars for Graphical models course at CMC MSU. Lecturers: Dmitry Vetrov, Dmitry Kropotov, 2012, 2013, 2014.
- Seminars for Graphical models course at Yandex Data Analysis School. Lecturers:
Victor Lempitsky, Dmitry Vetrov, 2011, 2012, 2013.
- Practical classes on Machine Learning at CMC MSU, 2012, 2013, 2014.
- Co-organizer of Bayesian methods of machine learning seminar at CMC MSU (together with Dmitry Vetrov and Dmitry Kropotov), 2010-2014.