2024-03-21 : INT-CONECT seminar by Ronan Sicre

“Visual interpretability: saliency maps and interpretable classification”


Date
2024-03-21 312:30
  • When: Thursday, March 21th 12:30 to 13:30
  • Where: salle Vinay

During this INT/CONECT seminar, Pr Ronan Sicre will present his recent work on “Visual interpretability: saliency maps and interpretable classification.”

Abstract : We will first review previous work on visual interpretability methods and particularly saliency-based methods. We will then present Opti-CAM, a CAM-based method that optimizes a masking objective per instance. The resulting saliency map highlights the important area of an image regarding the decision of a trained image classification network. Then, we will review some works around interpretable image classification using parts or prototype-based architectures.

Assistant professor at Ecole Centrale Marseille and research at team QARMA in LIS laboratory. Affiliations: Centrale Marseille, Aix Marseille Univ, CNRS, LIS, Marseille, France. Teaching Computer Science, Data Science, Machine Learning, and Computer Vision courses at ECM. Working on Machine Learning and Computer Vision
Matthieu Gilson
Matthieu Gilson
Researcher in Computational Neuroscience

Computational Neuroscience for Cognition and Neuropahtologies