480 citations · 724 across the 18 of their papers we have counts for
20 papers
How to make effective use of domain experts for image classification?
Dieu-Donné Fangnon, Diane Lingrand, Aurélie Liard +3
A lot of expectations have been put for years on integrating domain expert knowledge in image classification models. Several approaches have been explored, Concept Bottleneck Model…
Attention Meets Post-hoc Interpretability: A Mathematical Perspective
Gianluigi Lopardo, Frederic Precioso, Damien Garreau
Attention-based architectures, in particular transformers, are at the heart of a technological revolution. Interestingly, in addition to helping obtain state-of-the-art results on…
Visual Objectification in Films: Towards a New AI Task for Video Interpretation
Julie Tores, Lucile Sassatelli, Hui-Yin Wu +8
In film gender studies, the concept of 'male gaze' refers to the way the characters are portrayed on-screen as objects of desire rather than subjects. In this article, we introduce…
Faithful and Robust Local Interpretability for Textual Predictions
Gianluigi Lopardo, Frederic Precioso, Damien Garreau
Interpretability is essential for machine learning models to be trusted and deployed in critical domains. However, existing methods for interpreting text models are often complex,…
Interpretable Neural-Symbolic Concept Reasoning
Pietro Barbiero, Gabriele Ciravegna, Francesco Giannini +7
Deep learning methods are highly accurate, yet their opaque decision process prevents them from earning full human trust. Concept-based models aim to address this issue by learning…
Understanding Post-hoc Explainers: The Case of Anchors
Gianluigi Lopardo, Frederic Precioso, Damien Garreau
In many scenarios, the interpretability of machine learning models is a highly required but difficult task. To explain the individual predictions of such models, local model-agnost…
Sparse and geometry-aware generalisation of the mutual information for joint discriminative clustering and feature selection
Louis Ohl, Pierre-Alexandre Mattei, Charles Bouveyron +3
Feature selection in clustering is a hard task which involves simultaneously the discovery of relevant clusters as well as relevant variables with respect to these clusters. While…
Generalised Mutual Information for Discriminative Clustering
Louis Ohl, Pierre-Alexandre Mattei, Charles Bouveyron +4
In the last decade, recent successes in deep clustering majorly involved the mutual information (MI) as an unsupervised objective for training neural networks with increasing regul…
Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off
Mateo Espinosa Zarlenga, Pietro Barbiero, Gabriele Ciravegna +9
Deploying AI-powered systems requires trustworthy models supporting effective human interactions, going beyond raw prediction accuracy. Concept bottleneck models promote trustworth…
A Multi-stage deep architecture for summary generation of soccer videos
Melissa Sanabria, Frédéric Precioso, Pierre-Alexandre Mattei +1
Video content is present in an ever-increasing number of fields, both scientific and commercial. Sports, particularly soccer, is one of the industries that has invested the most in…
A Sea of Words: An In-Depth Analysis of Anchors for Text Data
Gianluigi Lopardo, Frederic Precioso, Damien Garreau
Anchors (Ribeiro et al., 2018) is a post-hoc, rule-based interpretability method. For text data, it proposes to explain a decision by highlighting a small set of words (an anchor)…
SMACE: A New Method for the Interpretability of Composite Decision Systems
Gianluigi Lopardo, Damien Garreau, Frederic Precioso +1
Interpretability is a pressing issue for decision systems. Many post hoc methods have been proposed to explain the predictions of a single machine learning model. However, business…
Knowledge-driven Active Learning
Gabriele Ciravegna, Frédéric Precioso, Alessandro Betti +2
The deployment of Deep Learning (DL) models is still precluded in those contexts where the amount of supervised data is limited. To answer this issue, active learning strategies ai…
Active Speaker Detection as a Multi-Objective Optimization with Uncertainty-based Multimodal Fusion
Baptiste Pouthier, Laurent Pilati, Leela K. Gudupudi +2
It is now well established from a variety of studies that there is a significant benefit from combining video and audio data in detecting active speakers. However, either of the mo…
From text saliency to linguistic objects: learning linguistic interpretable markers with a multi-channels convolutional architecture
Laurent Vanni, Marco Corneli, Damon Mayaffre +1
A lot of effort is currently made to provide methods to analyze and understand deep neural network impressive performances for tasks such as image or text classification. These met…
Revisiting Deep Architectures for Head Motion Prediction in 360° Videos
Miguel Fabian Romero Rondon, Lucile Sassatelli, Ramon Aparicio Pardo +1
We consider predicting the user's head motion in 360-degree videos, with 2 modalities only: the past user's positions and the video content (not knowing other users' traces). We ma…
Adaptive Bayesian Linear Regression for Automated Machine Learning
Weilin Zhou, Frederic Precioso
To solve a machine learning problem, one typically needs to perform data preprocessing, modeling, and hyperparameter tuning, which is known as model selection and hyperparameter op…
Adversarial Active Learning for Deep Networks: a Margin Based Approach
Melanie Ducoffe, Frederic Precioso
We propose a new active learning strategy designed for deep neural networks. The goal is to minimize the number of data annotation queried from an oracle during training. Previous…
QBDC: Query by dropout committee for training deep supervised architecture
Melanie Ducoffe, Frederic Precioso
While the current trend is to increase the depth of neural networks to increase their performance, the size of their training database has to grow accordingly. We notice an emergen…
Assessment of algorithms for mitosis detection in breast cancer histopathology images
Mitko Veta, Paul J. van Diest, Stefan M. Willems +26
The proliferative activity of breast tumors, which is routinely estimated by counting of mitotic figures in hematoxylin and eosin stained histology sections, is considered to be on…