Selected Publications

In this paper, we study a nonconvex continuous relaxation of MAP inference in discrete Markov random fields (MRFs). We show that for arbitrary MRFs, this relaxation is tight, and a discrete stationary point of it can be easily reached by a simple block coordinate descent algorithm. In addition, we study the resolution of this relaxation using popular gradient methods, and further propose a more effective solution using a multilinear decomposition framework based on the alternating direction method of multipliers (ADMM). Experiments on many real-world problems demonstrate that the proposed ADMM significantly outperforms other nonconvex relaxation based methods, and compares favorably with state of the art MRF optimization algorithms in different settings.
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018

We introduce a graph matching method that can account for constraints of arbitrary order, with arbitrary potential functions. Unlike previous decomposition approaches that rely on the graph structures, we introduce a decomposition of the matching constraints. Graph matching is then reformulated as a non-convex non-separable optimization problem that can be split into smaller and much-easier-to-solve subproblems, by means of the alternating direction method of multipliers. The proposed framework is modular, scalable, and can be instantiated into different variants. Two instantiations are studied exploring pairwise and higher-order constraints. Experimental results on widely adopted benchmarks involving synthetic and real examples demonstrate that the proposed solutions outperform existing pairwise graph matching methods, and competitive with the state of the art in higher-order settings.
In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017

Recent Publications

. Continuous Relaxation of MAP Inference: A Nonconvex Perspective. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.

PDF

. Alternating Direction Graph Matching. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.

PDF Code Supplement

. An Active Contour Model with Improved Shape Priors Using Fourier Descriptors. International Conference on Computer Vision Theory and Applications (VISAPP), 2013.

PDF Code

Community activities

I have been a reviewer for the following journals:

  • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).
  • International Journal of Computer Vision (IJCV).

Teaching

I have been a teaching assistant and/or a guest lecturer for the following MSc programs of CentraleSupélec.

MSc in Data Sciences & Business Analytics

  • 2017-2018: Applied Mathematics (including Machine Learning, Statistics, Continuous and Discrete Optimization)

MSc in Applied Mathematics: Vision and Learning

  • 2017-2018: Discrete Inference and Learning
  • 2016-2017: Introduction to Deep Learning
  • 2015-2016: Machine Learning for Computer Vision
  • 2014-2015: Machine Learning for Computer Vision

Contact

  • [email protected]
  • Center for Visual Computing, CentraleSupélec, 8-10 rue Joliot-Curie, 91192 Gif-sur-Yvette, France