# Black Box Explanation by Learning Image Exemplars in the Latent Feature Space

arXiv: https://arxiv.org/abs/2002.03746 · HTML: https://mlsanity.com/paper/2002.03746/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jan 2020.

## Built on by (most cited first, 23 of 23)

- [Benchmarking and Survey of Explanation Methods for Black Box Models](https://mlsanity.com/paper/2102.13076/) (2021)
- [Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond](https://mlsanity.com/paper/2103.10689/) (2021)
- [Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applications](https://mlsanity.com/paper/2103.04244/) (2021)
- [Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations](https://mlsanity.com/paper/2103.10226/) (2021)
- [NoiseGrad: Enhancing Explanations by Introducing Stochasticity to Model Weights](https://mlsanity.com/paper/2106.10185/) (2021)
- [Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspective](https://mlsanity.com/paper/2401.04374/) (2024)
- [Benchmarking Instance-Centric Counterfactual Algorithms for XAI: From White Box to Black Box](https://mlsanity.com/paper/2203.02399/) (2022)
- [Explaining Classifiers by Constructing Familiar Concepts](https://mlsanity.com/paper/2203.04109/) (2022)
- [Understanding Prediction Discrepancies in Machine Learning Classifiers](https://mlsanity.com/paper/2104.05467/) (2021)
- [XPROAX-Local explanations for text classification with progressive neighborhood approximation](https://mlsanity.com/paper/2109.15004/) (2021)
- [Interpretable Summaries of Black Box Incident Triaging with Subgroup Discovery](https://mlsanity.com/paper/2108.03013/) (2021)
- [Exemplars and Counterexemplars Explanations for Image Classifiers, Targeting Skin Lesion Labeling](https://mlsanity.com/paper/2302.03033/) (2023)
- [Analogies and Feature Attributions for Model Agnostic Explanation of Similarity Learners](https://mlsanity.com/paper/2202.01153/) (2022)
- [Anomaly Detection in Event-triggered Traffic Time Series via Similarity Learning](https://mlsanity.com/paper/2506.16855/) (2025)
- [Explainable Deep Image Classifiers for Skin Lesion Diagnosis](https://mlsanity.com/paper/2111.11863/) (2021)
- [Explaining text classifiers through progressive neighborhood approximation with realistic samples](https://mlsanity.com/paper/2302.07733/) (2023)
- [Transparent Neighborhood Approximation for Text Classifier Explanation](https://mlsanity.com/paper/2411.16251/) (2024)
- [Explainable Artificial Intelligence in Biomedical Image Analysis: A Comprehensive Survey](https://mlsanity.com/paper/2507.07148/) (2025)
- [Axiomatic Foundations of Counterfactual Explanations](https://mlsanity.com/paper/2602.04028/) (2026)
- [Decomposing Counterfactual Explanations for Consequential Decision Making](https://mlsanity.com/paper/2211.02151/) (2022)
- [Hub-VAE: Unsupervised Hub-based Regularization of Variational Autoencoders](https://mlsanity.com/paper/2211.10469/) (2022)
- [Causality-Aware Local Interpretable Model-Agnostic Explanations](https://mlsanity.com/paper/2212.05256/) (2022)
- [Explainable AI in Time-Sensitive Scenarios: Prefetched Offline Explanation Model](https://mlsanity.com/paper/2503.04283/) (2025)

## Abstract (arXiv)

We present an approach to explain the decisions of black box models for image classification. While using the black box to label images, our explanation method exploits the latent feature space learned through an adversarial autoencoder. The proposed method first generates exemplar images in the latent feature space and learns a decision tree classifier. Then, it selects and decodes exemplars respecting local decision rules. Finally, it visualizes them in a manner that shows to the user how the exemplars can be modified to either stay within their class, or to become counter-factuals by "morphing" into another class. Since we focus on black box decision systems for image classification, the explanation obtained from the exemplars also provides a saliency map highlighting the areas of the image that contribute to its classification, and areas of the image that push it into another class. We present the results of an experimental evaluation on three datasets and two black box models. Besides providing the most useful and interpretable explanations, we show that the proposed method outperforms existing explainers in terms of fidelity, relevance, coherence, and stability.