mlsanityData to 14 Oct 2026

Clarity: an improved gradient method for producing quality visual counterfactual explanations

arXiv 2211.15370 ↗First posted 22 Nov 2022cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Visual counterfactual explanations identify modifications to an image that would change the prediction of a classifier. We propose a set of techniques based on generative models (VAE) and a classifier ensemble directly trained in the latent space, which all together, improve the quality of the gradient required to compute visual counterfactuals. These improvements lead to a novel classification model, Clarity, which produces realistic counterfactual explanations over all images. We also present several experiments that give insights on why these techniques lead to better quality results than those in the literature. The explanations produced are competitive with the state-of-the-art and emphasize the importance of selecting a meaningful input space for training.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 34 references that are in the map. First posted on arXiv 22 Nov 2022.

Builds on

27 of 34 references.

References · 27

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  4. 2022Generative Adversarial Networkscited by 5,627
  5. 2013Intriguing properties of neural networkscited by 5,155
  6. 2013Auto-Encoding Variational Bayescited by 4,053
  7. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  8. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  9. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  10. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  11. 2015Variational Inference with Normalizing Flowscited by 2,170
  12. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,089
15 more
  1. 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
  2. 2019Counterfactual Visual Explanationscited by 313
  3. 2019Interpretable Counterfactual Explanations Guided by Prototypescited by 223
  4. 2019Diagnosing and Enhancing VAE Modelscited by 193
  5. 2018Understanding Measures of Uncertainty for Adversarial Example Detectioncited by 177
  6. 2018Explaining Image Classifiers by Counterfactual Generationcited by 144
  7. 2019Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systemscited by 131
  8. 2021Explaining in Style: Training a GAN to explain a classifier in StyleSpacecited by 122
  9. 2022Diffusion Causal Models for Counterfactual Estimationcited by 87
  10. 2021If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniquescited by 82
  11. 2020The Intriguing Relation Between Counterfactual Explanations and Adversarial Examplescited by 44
  12. 2021Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertaintiescited by 41
  13. 2019Generative Counterfactual Introspection for Explainable Deep Learningcited by 36
  14. 2022Sparse Visual Counterfactual Explanations in Image Spacecited by 30
  15. 2021DeDUCE: Generating Counterfactual Explanations Efficientlycited by 6

Built on by

Not cited yet.