Skip to Main content
Number of documents

9

Assistant professor at ENSTA Paris


I'm an assistant professor in the U2IS  at ENSTA Paris. My research focuses on theoretical deep learning. I'm interested in uncertainty and deep learning,  statistical models, semi-supervised learning, domain adaptation, etc ...


Journal articles2 documents

  • Gianni Franchi, Nacim Belkhir, Mai Lan Ha, Yufei Hu, Andrei Bursuc, et al.. Robust Semantic Segmentation with Superpixel-Mix. Proceedings of the British Machine Vision Conference, In press. ⟨hal-03400621⟩
  • Xuanlong Yu, Gianni Franchi, Emanuel Aldea. SLURP: Side Learning Uncertainty for Regression Problems. Proceedings of the British Machine Vision Conference, In press. ⟨hal-03400658⟩

Conference papers5 documents

  • Gianni Franchi, Andrei Bursuc, Emanuel Aldea, Séverine Dubuisson, Isabelle Bloch. One Versus all for deep Neural Network Incertitude (OVNNI) quantification. NeurIPS workshop on Bayesian Deep Learning, Dec 2020, Vancouver, Canada. ⟨hal-03097063⟩
  • Gianni Franchi, Andrei Bursuc, Emanuel Aldea, Séverine Dubuisson, Isabelle Bloch. Encoding the latent posterior of Bayesian Neural Networks for uncertainty quantification. NeurIPS workshop on Bayesian Deep Learning, Dec 2020, Vancouver, Canada. ⟨hal-03097035v2⟩
  • G. Franchi, A. Bursuc, E. Aldea, Séverine Dubuisson, Isabelle Bloch. TRADI: Tracking deep neural network weight distributions. European Conference on Computer Vision (ECCV), 2020, Glasgow, United Kingdom. ⟨hal-02916159⟩
  • G. Franchi, E. Aldea, Séverine Dubuisson, Isabelle Bloch. Tracking hundreds of people in densely crowded scenes with particle filtering supervising deep convolutional neural networks. IEEE International Conference on Image Processing (ICIP), 2020, Abu Dhabi, Unknown Region. ⟨hal-02916158⟩
  • Gianni Franchi, E. Aldea, S. Dubuisson, Isabelle Bloch. Crowd Behaviour Characterization for Scene Tracking. IEEE International Conference on Advanced Video and Signal-based Surveillance (AVSS), 2019, Taipei, Taiwan. ⟨hal-02288288⟩

Reports1 document

  • Gianni Franchi, Andrei Bursuc, Emmanuel Aldea, Séverine Dubuisson, Isabelle Bloch. TRADI: Tracking deep neural network weight distributions. [Research Report] Telecom Paristech; LTCI - Laboratoire Traitement et Communication de l'Information [Paris]. 2019. ⟨hal-02428596⟩

Theses1 document