Search Results for author:
Found 8 papers, 4 papers with code
Text-to-Image Models for Counterfactual Explanations: a Black-Box Approach
This paper addresses the challenge of generating Counterfactual Explanations (CEs), involving the identification and modification of the fewest necessary features to alter a classifier's prediction for a given image.
Adversarial Counterfactual Visual Explanations
Counterfactual explanations and adversarial attacks have a related goal: flipping output labels with minimal perturbations regardless of their characteristics.
Diffusion Models for Counterfactual Explanations
Counterfactual explanations have shown promising results as a post-hoc framework to make image classifiers more explainable.
On the inductive biases of deep domain adaptation
Domain alignment is currently the most prevalent solution to unsupervised domain-adaptation tasks and are often being presented as minimizers of some theoretical upper-bounds on risk in the target domain.
n-MeRCI: A new Metric to Evaluate the Correlation Between Predictive Uncertainty and True Error
As deep learning applications are becoming more and more pervasive in robotics, the question of evaluating the reliability of inferences becomes a central question in the robotics community.
Revisiting Precision and Recall Definition for Generative Model Evaluation
In this article we revisit the definition of Precision-Recall (PR) curves for generative models proposed by Sajjadi et al. (arXiv:1806. 00035).
MERCI: A NEW METRIC TO EVALUATE THE CORRELATION BETWEEN PREDICTIVE UNCERTAINTY AND TRUE ERROR
One contribution of this article is to draw attention on existing metrics developed in the forecast community, designed to evaluate both the sharpness and the calibration of predictive uncertainty.
An Adversarial Regularisation for Semi-Supervised Training of Structured Output Neural Networks
We propose a method for semi-supervised training of structured-output neural networks.
