Thomas Fréour

According to our database, Thomas Fréour authored at least 6 papers between 2021 and 2022.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2022

BR-NPA: A non-parametric high-resolution attention model to improve the interpretability of attention.

Tristan Gomez, Suiyi Ling, Thomas Fréour, Harold Mouchère

Pattern Recognit., 2022

Towards deep learning-powered IVF: A large public benchmark for morphokinetic parameter prediction.

Tristan Gomez, Magalie Feyeux, Nicolas Normand, Laurent David, Perrine Paul-Gilloteaux, Thomas Fréour, Harold Mouchère

CoRR, 2022

Super-Focus: Domain Adaptation for Embryo Imaging via Self-supervised Focal Plane Regression.

Chloe He, Céline Jacques, Jérôme Chambost, Jonas Malmsten, Koen Wouters, Thomas Fréour, Nikica Zaninovic, Cristina Hickman, Francisco Vasconcelos

Proceedings of the Medical Image Computing and Computer Assisted Intervention - MICCAI 2022, 2022

Metrics for Saliency Map Evaluation of Deep Learning Explanation Methods.

Tristan Gomez, Thomas Fréour, Harold Mouchère

Proceedings of the Pattern Recognition and Artificial Intelligence, 2022

Comparison of Attention Models and Post-hoc Explanation Methods for Embryo Stage Identification: A Case Study.

Tristan Gomez, Thomas Fréour, Harold Mouchère

Proceedings of the Pattern Recognition, Computer Vision, and Image Processing. ICPR 2022 International Workshops and Challenges, 2022

2021

Improve the Interpretability of Attention: A Fast, Accurate, and Interpretable High-Resolution Attention Model.

Tristan Gomez, Suiyi Ling, Thomas Fréour, Harold Mouchère

CoRR, 2021