# Explanation by Progressive Exaggeration

arXiv: https://arxiv.org/abs/1911.00483 · HTML: https://mlsanity.com/paper/1911.00483/

## Key facts

- Cited by 76 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Nov 2019.

## Built on by (most cited first, 30 of 76)

- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Explaining in Style: Training a GAN to explain a classifier in StyleSpace](https://mlsanity.com/paper/2104.13369/) (2021)
- [If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniques](https://mlsanity.com/paper/2103.01035/) (2021)
- [Explainability of deep vision-based autonomous driving systems: Review and challenges](https://mlsanity.com/paper/2101.05307/) (2021)
- [Diffusion Models for Counterfactual Explanations](https://mlsanity.com/paper/2203.15636/) (2022)
- [Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations](https://mlsanity.com/paper/2103.10226/) (2021)
- [Meaningfully Debugging Model Mistakes using Conceptual Counterfactual Explanations](https://mlsanity.com/paper/2106.12723/) (2021)
- [Adversarial Counterfactual Visual Explanations](https://mlsanity.com/paper/2303.09962/) (2023)
- [Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generation](https://mlsanity.com/paper/2312.14223/) (2023)
- [STEEX: Steering Counterfactual Explanations with Semantics](https://mlsanity.com/paper/2111.09094/) (2021)
- [DISSECT: Disentangled Simultaneous Explanations via Concept Traversals](https://mlsanity.com/paper/2105.15164/) (2021)
- [Global Concept-Based Interpretability for Graph Neural Networks via Neuron Analysis](https://mlsanity.com/paper/2208.10609/) (2022)
- [Making Heads or Tails: Towards Semantically Consistent Visual Counterfactuals](https://mlsanity.com/paper/2203.12892/) (2022)
- [Diffeomorphic Counterfactuals with Generative Models](https://mlsanity.com/paper/2206.05075/) (2022)
- [OCTET: Object-aware Counterfactual Explanations](https://mlsanity.com/paper/2211.12380/) (2022)
- [Text-to-Image Models for Counterfactual Explanations: a Black-Box Approach](https://mlsanity.com/paper/2309.07944/) (2023)
- [Robust Feature-Level Adversaries are Interpretability Tools](https://mlsanity.com/paper/2110.03605/) (2021)
- [Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution](https://mlsanity.com/paper/2401.15866/) (2024)
- [Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimates](https://mlsanity.com/paper/2112.02646/) (2021)
- [CounterNet: End-to-End Training of Prediction Aware Counterfactual Explanations](https://mlsanity.com/paper/2109.07557/) (2021)
- [PRISM: High-Resolution & Precise Counterfactual Medical Image Generation using Language-guided Stable Diffusion](https://mlsanity.com/paper/2503.00196/) (2025)
- [The Manifold Hypothesis for Gradient-Based Explanations](https://mlsanity.com/paper/2206.07387/) (2022)
- [Right for the Wrong Reason: Can Interpretable ML Techniques Detect Spurious Correlations?](https://mlsanity.com/paper/2307.12344/) (2023)
- [Designing Counterfactual Generators using Deep Model Inversion](https://mlsanity.com/paper/2109.14274/) (2021)
- [Global Counterfactual Directions](https://mlsanity.com/paper/2404.12488/) (2024)
- [Efficient XAI Techniques: A Taxonomic Survey](https://mlsanity.com/paper/2302.03225/) (2023)
- [Rethinking Visual Counterfactual Explanations Through Region Constraint](https://mlsanity.com/paper/2410.12591/) (2024)
- [Do Users Benefit From Interpretable Vision? A User Study, Baseline, And Dataset](https://mlsanity.com/paper/2204.11642/) (2022)
- [Counterfactual Explanations for Misclassified Images: How Human and Machine Explanations Differ](https://mlsanity.com/paper/2212.08733/) (2022)
- [Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation](https://mlsanity.com/paper/2101.06930/) (2021)

## Abstract (arXiv)

As machine learning methods see greater adoption and implementation in high stakes applications such as medical image diagnosis, the need for model interpretability and explanation has become more critical. Classical approaches that assess feature importance (e.g. saliency maps) do not explain how and why a particular region of an image is relevant to the prediction. We propose a method that explains the outcome of a classification black-box by gradually exaggerating the semantic effect of a given class. Given a query input to a classifier, our method produces a progressive set of plausible variations of that query, which gradually changes the posterior probability from its original class to its negation. These counter-factually generated samples preserve features unrelated to the classification decision, such that a user can employ our method as a "tuning knob" to traverse a data manifold while crossing the decision boundary. Our method is model agnostic and only requires the output value and gradient of the predictor with respect to its input.