Gianni Franchi
19
Documents
Présentation
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 ...
Publications
|
Encoding the Latent Posterior of Bayesian Neural Networks for Uncertainty QuantificationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46 (4), pp.2027-2040. ⟨10.1109/TPAMI.2023.3328829⟩
Article dans une revue
hal-04320979v1
|
Learning deep morphological networks with neural architecture searchPattern Recognition, 2022, 131, pp.108893. ⟨10.1016/j.patcog.2022.108893⟩
Article dans une revue
hal-03775894v1
|
|
|
One Versus all for deep Neural Network Incertitude (OVNNI) quantificationIEEE Access, 2022, ⟨10.1109/access.2021.3138978⟩
Article dans une revue
hal-03097063v1
|
|
EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: The MonuMAI cultural heritage use caseInformation Fusion, 2021, ⟨10.1016/j.inffus.2021.09.022⟩
Article dans une revue
hal-03379551v1
|
|
Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regression38th AAAI Conference on Artificial Intelligence (AAAI-24), Feb 2024, Vancouvert, Canada. ⟨10.48550/arXiv.2308.09065⟩
Communication dans un congrès
hal-04480649v1
|
|
NECO: NEURAL COLLAPSE BASED OUT-OF-DISTRIBUTION DETECTIONThe Twelfth International Conference on Learning Representations, May 2024, Vienne (AUT), France
Communication dans un congrès
hal-04480548v1
|
A Symmetry-Aware Exploration of Bayesian Neural Network Posteriors12th International Conference on Learning Representations. ICLR 2024, May 2024, Vienna, Austria
Communication dans un congrès
hal-04480585v1
|
|
InfraParis: A multi-modal and multi-task autonomous driving datasetWACV 2024 - IEEE/CVF Winter Conference on Applications of Computer Vision, Jan 2024, Waikoloa, United States
Communication dans un congrès
hal-04321062v1
|
|
Learning to Generate Training Datasets for Robust Semantic SegmentationIEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Jan 2024, WAIKOLOA, United States
Communication dans un congrès
hal-04321102v1
|
|
|
The Robust Semantic Segmentation UNCV2023 Challenge Results2023 IEEE/CVF International Conference on Computer Vision (ICCVW) Workshops, Oct 2023, Paris, France. pp.4620-4630, ⟨10.1109/iccvw60793.2023.00496⟩
Communication dans un congrès
hal-04321188v1
|
|
MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and tasks33rd British Machine Vision Conference, Nov 2022, London, United Kingdom
Communication dans un congrès
hal-04454911v1
|
|
On Monocular Depth Estimation and Uncertainty Quantification using Classification Approaches for Regression29th IEEE International Conference on Image Processing (IEEE ICIP), Oct 2022, Bordeaux, France. ⟨10.1109/ICIP46576.2022.9897930⟩
Communication dans un congrès
hal-03775941v1
|
|
Latent Discriminant deterministic UncertaintyEuropean Conference on Computer Vision (ECCV 2022), Oct 2022, Tel Aviv,, Israel. ⟨10.1007/978-3-031-19775-8_15⟩
Communication dans un congrès
hal-03775954v1
|
SLURP: Side Learning Uncertainty for Regression ProblemsThe 32nd British Machine Vision Conference, Nov 2021, Online, United Kingdom
Communication dans un congrès
hal-03400658v1
|
|
Robust Semantic Segmentation with Superpixel-MixThe British Machine Vision Conference (BMVC), Nov 2021, Online, United Kingdom
Communication dans un congrès
hal-03400621v1
|
|
|
Encoding the latent posterior of Bayesian Neural Networks for uncertainty quantificationNeurIPS workshop on Bayesian Deep Learning, Dec 2020, Vancouver, Canada
Communication dans un congrès
hal-03097035v2
|
Tracking hundreds of people in densely crowded scenes with particle filtering supervising deep convolutional neural networksIEEE International Conference on Image Processing (ICIP), 2020, Abu Dhabi, Unknown Region. ⟨10.1109/ICIP40778.2020.9190953⟩
Communication dans un congrès
hal-02916158v1
|
TRADI: Tracking deep neural network weight distributions[Research Report] Telecom Paristech; LTCI - Laboratoire Traitement et Communication de l'Information [Paris]. 2019
Rapport
hal-02428596v1
|
|
Spatial machine learning applied to multivariate and multimodal imagesImage Processing [eess.IV]. Université Paris sciences et lettres, 2016. English. ⟨NNT : 2016PSLEM071⟩
Thèse
tel-01483980v2
|