← Search

Paul Novello

3 accepted papers

2023

Robust One-Class Classification with Signed Distance Function using 1-Lipschitz Neural Networks

ICML 2023poster

We propose a new method, dubbed One Class Signed Distance Function (OCSDF), to perform One Class Classification (OCC) by provably learning the Signed Distance Function (SDF) to the boundary of the support of any distribution. The distance to the support can be interpreted as a normality score, and i…

2023

Unlocking Feature Visualization for Deep Network with MAgnitude Constrained Optimization

NeurIPS 2023poster

Feature visualization has gained significant popularity as an explainability method, particularly after the influential work by Olah et al. in 2017. Despite its success, its widespread adoption has been limited due to issues in scaling to deeper neural networks and the reliance on tricks to generate…

Cited by 19SourcePDFScholar
2022

Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure

NeurIPS 2022accept

This paper presents a new efficient black-box attribution method built on Hilbert-Schmidt Independence Criterion (HSIC). Based on Reproducing Kernel Hilbert Spaces (RKHS), HSIC measures the dependence between regions of an input image and the output of a model using the kernel embedding of their dis…