518 citations
- Centre National de la Recherche ScientifiqueFR186 papers
- Université Toulouse III - Paul SabatierFR125 papers
- Institut de Recherche en Informatique de ToulouseFR124 papers
- Université Toulouse-I-CapitoleFR124 papers
- Université Toulouse - Jean JaurèsFR124 papers
- Université de BordeauxFR114 papers
- Institut de Mathématiques de MarseilleFR102 papers
- Château GombertFR67 papers
- Laboratoire Bordelais de Recherche en InformatiqueFR67 papers
- Aix-Marseille UniversitéFR38 papers
- Centrale MéditerranéeFR37 papers
- Institut de Mécanique et d'Ingénierie de BordeauxFR31 papers
11 papers · 1 filter
Evaluation of Explanation Methods of AI -- CNNs in Image Classification Tasks with Reference-based and No-reference Metrics
A. Zhukov, J. Benois-Pineau, R. Giot
The most popular methods in AI-machine learning paradigm are mainly black boxes. This is why explanation of AI decisions is of emergency. Although dedicated explanation tools have…
Three-Stream 3D/1D CNN for Fine-Grained Action Classification and Segmentation in Table Tennis
Pierre-Etienne Martin, Jenny Benois-Pineau, Renaud Péteri +1
This paper proposes a fusion method of modalities extracted from video through a three-stream network with spatio-temporal and temporal convolutions for fine-grained action classif…
Natural vs Balanced Distribution in Deep Learning on Whole Slide Images for Cancer Detection
Ismat Ara Reshma, Sylvain Cussat-Blanc, Radu Tudor Ionescu +2
The class distribution of data is one of the factors that regulates the performance of machine learning models. However, investigations on the impact of different distributions ava…
3D attention mechanism for fine-grained classification of table tennis strokes using a Twin Spatio-Temporal Convolutional Neural Networks
Pierre-Etienne Martin, Jenny Benois-Pineau, Renaud Péteri +1
The paper addresses the problem of recognition of actions in video with low inter-class variability such as Table Tennis strokes. Two stream, "twin" convolutional neural networks a…
Satellite Image Time Series Classification with Pixel-Set Encoders and Temporal Self-Attention
Vivien Sainte Fare Garnot, Loic Landrieu, Sebastien Giordano +1
Satellite image time series, bolstered by their growing availability, are at the forefront of an extensive effort towards automated Earth monitoring by international institutions.…
Cost-Effective Active Learning for Melanoma Segmentation
Marc Gorriz, Axel Carlier, Emmanuel Faure +1
We propose a novel Active Learning framework capable to train effectively a convolutional neural network for semantic segmentation of medical imaging, with a limited amount of trai…