activity
20182022
most citedOne Versus all for deep Neural Network Incertitude (OVNNI) quantification

9 citations · 26 across the 6 of their papers we have counts for

collaborators

9 papers

cs.CV20222 cited

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

Adrien Bennetot, Gianni Franchi, Javier Del Ser +2

Although Deep Neural Networks (DNNs) have great generalization and prediction capabilities, their functioning does not allow a detailed explanation of their behavior. Opaque deep l…

cs.CV20226 cited

A study of deep perceptual metrics for image quality assessment

Rémi Kazmierczak, Gianni Franchi, Nacim Belkhir +2

Several metrics exist to quantify the similarity between images, but they are inefficient when it comes to measure the similarity of highly distorted images. In this work, we propo…

cs.CV20216 cited

Robust Semantic Segmentation with Superpixel-Mix

Gianni Franchi, Nacim Belkhir, Mai Lan Ha +4

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

cs.CV20211 cited

Learning a Discriminant Latent Space with Neural Discriminant Analysis

Mai Lan Ha, Gianni Franchi, Emanuel Aldea +1

Discriminative features play an important role in image and object classification and also in other fields of research such as semi-supervised learning, fine-grained classification…

cs.LG2021

EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage use case

Natalia Díaz-Rodríguez, Alberto Lamas, Jules Sanchez +7

The latest Deep Learning (DL) models for detection and classification have achieved an unprecedented performance over classical machine learning algorithms. However, DL models are…

cs.CV20202 cited

Encoding the latent posterior of Bayesian Neural Networks for uncertainty quantification

Gianni Franchi, Andrei Bursuc, Emanuel Aldea +2

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. Whi…