Publications & Courses

Publications and research works

DualDis: Dual-Branch Disentangling with Adversarial Learning
T. Robert, N. Thome, M. Cord
Under review at NeurIPS (2019)

HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised Learning
T. Robert, N. Thome, M. Cord
Published at European Conference on Computer Vision (ECCV) (2018)

SHADE: Information-Based Regularization for Deep Learning
M. Blot, T. Robert, N. Thome, M. Cord
Published at IEEE International Conference on Image Processing (ICIP) (2018)
Best paper award

M2CAI workflow challenge: classification of surgical operation steps based on endosopic videos
R. Cadene, T. Robert, N. Thome, M. Cord
Published at M2CAI workshop, MICCAI (2016)
2ème position au challenge
[Technical article] [Slides] [Code]

VISIIR: deep learning for recipe image classification
T. Robert, R. Cadene, N. Thome, M. Cord
(2016) Demo and extension of a publication by our team
[Demo] [Related publication]



Deep Learning for Computer Vision (masters)

For the RDFIA courses (Reconnaissance de Formes et Intelligence Artificielle) handled by Matthieu Cord for students of french masters degree “IMA” and “DAC” at Sorbonne University. In charge of practice sessions. Writing of the subjects of the sessions on understanding and different uses of convolutional neural.

Subjects in french :

Java (bachelor)

In charge of practical sessions of Java for students in french “license 2″ (~2nd year of bachelor’s degree).