Explaining an image classifier with a generative model conditioned by uncertainty
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 18 of its 23 references that are in the map. First posted on arXiv 2 Oct 2024.
Builds on
18 of 23 references.
References · 18
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2022Generative Adversarial Networkscited by 5,603
- 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
- 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
- 2014Conditional Generative Adversarial Netscited by 2,152
- 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
- 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
- 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
- 2020StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generationcited by 331
- 2019Counterfactual Visual Explanationscited by 312
- 2017Generating Natural Adversarial Examplescited by 182
- 2021Explaining in Style: Training a GAN to explain a classifier in StyleSpacecited by 122
6 more
- 2021Counterfactual Generative Networkscited by 111
- 2023Adversarial Counterfactual Visual Explanationscited by 47
- 2022Discovering Bugs in Vision Models using Off-the-shelf Image Generation and Captioningcited by 45
- 2020Confidence Estimation via Auxiliary Modelscited by 33
- 2022UQGAN: A Unified Model for Uncertainty Quantification of Deep Classifiers trained via Conditional GANscited by 16
- 2024Leveraging generative models to characterize the failure conditions of image classifierscited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.