No confident code implementation found for this paper.
We propose to condition a generative model by a given image classifier uncertainty in order to analyze and explain its behavior. Preliminary experiments on synthetic data and a corrupted version of MNIST dataset illustrate the idea.
No confident code match yet
We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.
No code implementations found yet.
Know of an implementation? Let us know in the comments below!
Epistemic Uncertainty for Generated Image Detection
Leveraging generative models to characterize the failure conditions of image classifiers
MedSymmFlow: Bridging Generative Modeling and Classification in Medical Imaging through Symmetrical Flow Matching
Uncertainty-Aware Concept Bottleneck Models with Enhanced Interpretability
TSynD: Targeted Synthetic Data Generation for Enhanced Medical Image Classification
SURE: SUrvey REcipes for Building Reliable and Robust Deep Networks
@article{lecoz2024explaining,
title = {Explaining an image classifier with a generative model conditioned by uncertainty},
author = {Adrien LeCoz and Stéphane Herbin and Faouzi Adjed},
year = {2024},
eprint = {2410.13871},
archivePrefix = {arXiv},
url = {http://arxiv.org/abs/2410.13871v2}
}Shows whether official code is linked for this paper.
[](https://codeofpaper.com/paper/2410.13871)