Search Results for author: Gianni Franchi

Found 16 papers, 8 papers with code

Packed-Ensembles for Efficient Uncertainty Estimation

no code implementations17 Oct 2022 Olivier Laurent, Adrien Lafage, Enzo Tartaglione, Geoffrey Daniel, Jean-Marc Martinez, Andrei Bursuc, Gianni Franchi

Deep Ensembles (DE) are a prominent approach achieving excellent performance on key metrics such as accuracy, calibration, uncertainty estimation, and out-of-distribution detection.

Out-of-Distribution Detection

Greybox XAI: a Neural-Symbolic learning framework to produce interpretable predictions for image classification

no code implementations26 Sep 2022 Adrien Bennetot, Gianni Franchi, Javier Del Ser, Raja Chatila, Natalia Diaz-Rodriguez

As a result, there is a widespread agreement on the importance of endowing Deep Learning models with explanatory capabilities so that they can themselves provide an answer to why a particular prediction was made.

Explainable artificial intelligence Image Classification

Latent Discriminant deterministic Uncertainty

1 code implementation20 Jul 2022 Gianni Franchi, Xuanlong Yu, Andrei Bursuc, Emanuel Aldea, Severine Dubuisson, David Filliat

Predictive uncertainty estimation is essential for deploying Deep Neural Networks in real-world autonomous systems.

Autonomous Driving Image Classification +2

MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and tasks

1 code implementation2 Mar 2022 Gianni Franchi, Xuanlong Yu, Andrei Bursuc, Angel Tena, Rémi Kazmierczak, Séverine Dubuisson, Emanuel Aldea, David Filliat

However, disentangling the different types and sources of uncertainty is non trivial for most datasets, especially since there is no ground truth for uncertainty.

Anomaly Detection Autonomous Driving +4

On Monocular Depth Estimation and Uncertainty Quantification using Classification Approaches for Regression

no code implementations24 Feb 2022 Xuanlong Yu, Gianni Franchi, Emanuel Aldea

To this end, this paper will introduce a taxonomy and summary of CAR approaches, a new uncertainty estimation solution for CAR, and a set of experiments on depth accuracy and uncertainty quantification for CAR-based models on KITTI dataset.

3D Reconstruction Autonomous Driving +2

A study of deep perceptual metrics for image quality assessment

1 code implementation17 Feb 2022 Rémi Kazmierczak, Gianni Franchi, Nacim Belkhir, Antoine Manzanera, David Filliat

Several metrics exist to quantify the similarity between images, but they are inefficient when it comes to measure the similarity of highly distorted images.

Image Quality Assessment

SLURP: Side Learning Uncertainty for Regression Problems

1 code implementation21 Oct 2021 Xuanlong Yu, Gianni Franchi, Emanuel Aldea

It has become critical for deep learning algorithms to quantify their output uncertainties to satisfy reliability constraints and provide accurate results.

regression

Robust Semantic Segmentation with Superpixel-Mix

1 code implementation2 Aug 2021 Gianni Franchi, Nacim Belkhir, Mai Lan Ha, Yufei Hu, Andrei Bursuc, Volker Blanz, Angela Yao

Along with predictive performance and runtime speed, reliability is a key requirement for real-world semantic segmentation.

Data Augmentation Semi-Supervised Semantic Segmentation +1

Learning a Discriminant Latent Space with Neural Discriminant Analysis

no code implementations13 Jul 2021 Mai Lan Ha, Gianni Franchi, Emanuel Aldea, Volker Blanz

NDA transforms deep features to become more discriminative and, therefore, improves the performances in various tasks.

Classification Out-of-Distribution Detection

Learning Deep Morphological Networks with Neural Architecture Search

1 code implementation14 Jun 2021 Yufei Hu, Nacim Belkhir, Jesus Angulo, Angela Yao, Gianni Franchi

Using a combination of linear and non-linear procedures is critical for generating a sufficiently deep feature space.

Edge Detection Meta-Learning +1

Encoding the latent posterior of Bayesian Neural Networks for uncertainty quantification

1 code implementation4 Dec 2020 Gianni Franchi, Andrei Bursuc, Emanuel Aldea, Severine Dubuisson, Isabelle Bloch

Bayesian neural networks (BNNs) have been long considered an ideal, yet unscalable solution for improving the robustness and the predictive uncertainty of deep neural networks.

Bayesian Inference Decision Making Under Uncertainty +4

One Versus all for deep Neural Network Incertitude (OVNNI) quantification

no code implementations1 Jun 2020 Gianni Franchi, Andrei Bursuc, Emanuel Aldea, Severine Dubuisson, Isabelle Bloch

This is due to the fact that modern DNNs are usually uncalibrated and we cannot characterize their epistemic uncertainty.

TRADI: Tracking deep neural network weight distributions for uncertainty estimation

no code implementations ECCV 2020 Gianni Franchi, Andrei Bursuc, Emanuel Aldea, Severine Dubuisson, Isabelle Bloch

During training, the weights of a Deep Neural Network (DNN) are optimized from a random initialization towards a nearly optimum value minimizing a loss function.

General Classification Out-of-Distribution Detection +1

Supervised Deep Kriging for Single-Image Super-Resolution

no code implementations10 Dec 2018 Gianni Franchi, Angela Yao, Andreas Kolb

We propose a novel single-image super-resolution approach based on the geostatistical method of kriging.

Image Super-Resolution Single Image Super Resolution +1

Hyperspectral Image Classification with Support Vector Machines on Kernel Distribution Embeddings

no code implementations30 May 2016 Gianni Franchi, Jesus Angulo, Dino Sejdinovic

We propose a novel approach for pixel classification in hyperspectral images, leveraging on both the spatial and spectral information in the data.

Classification General Classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.