# SCOUT: Self-aware Discriminant Counterfactual Explanations

arXiv: https://arxiv.org/abs/2004.07769 · HTML: https://mlsanity.com/paper/2004.07769/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Apr 2020.

## Built on by (most cited first, 30 of 52)

- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [HIVE: Evaluating the Human Interpretability of Visual Explanations](https://mlsanity.com/paper/2112.03184/) (2021)
- [Interpretable Image Classification with Differentiable Prototypes Assignment](https://mlsanity.com/paper/2112.02902/) (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)
- [Diffusion Models for Counterfactual Explanations](https://mlsanity.com/paper/2203.15636/) (2022)
- ["Help Me Help the AI": Understanding How Explainability Can Support Human-AI Interaction](https://mlsanity.com/paper/2210.03735/) (2022)
- [Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering](https://mlsanity.com/paper/2207.12647/) (2022)
- [Adversarial Counterfactual Visual Explanations](https://mlsanity.com/paper/2303.09962/) (2023)
- [STEEX: Steering Counterfactual Explanations with Semantics](https://mlsanity.com/paper/2111.09094/) (2021)
- [Treble Counterfactual VLMs: A Causal Approach to Hallucination](https://mlsanity.com/paper/2503.06169/) (2025)
- [Cycle-Consistent Counterfactuals by Latent Transformations](https://mlsanity.com/paper/2203.15064/) (2022)
- [ProtoSeg: Interpretable Semantic Segmentation with Prototypical Parts](https://mlsanity.com/paper/2301.12276/) (2023)
- [Making Heads or Tails: Towards Semantically Consistent Visual Counterfactuals](https://mlsanity.com/paper/2203.12892/) (2022)
- [OCTET: Object-aware Counterfactual Explanations](https://mlsanity.com/paper/2211.12380/) (2022)
- [ECINN: Efficient Counterfactuals from Invertible Neural Networks](https://mlsanity.com/paper/2103.13701/) (2021)
- [IMAGINE: Image Synthesis by Image-Guided Model Inversion](https://mlsanity.com/paper/2104.05895/) (2021)
- [ICICLE: Interpretable Class Incremental Continual Learning](https://mlsanity.com/paper/2303.07811/) (2023)
- [Counterfactual Image Editing](https://mlsanity.com/paper/2403.09683/) (2024)
- [Evolving Interpretable Visual Classifiers with Large Language Models](https://mlsanity.com/paper/2404.09941/) (2024)
- [Visual Causal Scene Refinement for Video Question Answering](https://mlsanity.com/paper/2305.04224/) (2023)
- [Learn-Explain-Reinforce: Counterfactual Reasoning and Its Guidance to Reinforce an Alzheimer's Disease Diagnosis Model](https://mlsanity.com/paper/2108.09451/) (2021)
- [Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning](https://mlsanity.com/paper/2310.19559/) (2023)
- [IG2: Integrated Gradient on Iterative Gradient Path for Feature Attribution](https://mlsanity.com/paper/2406.10852/) (2024)
- [Instance-wise or Class-wise? A Tale of Neighbor Shapley for Concept-based Explanation](https://mlsanity.com/paper/2109.01369/) (2021)
- [Towards Effective Human-AI Decision-Making: The Role of Human Learning in Appropriate Reliance on AI Advice](https://mlsanity.com/paper/2310.02108/) (2023)
- [Explainable Diabetic Retinopathy Detection and Retinal Image Generation](https://mlsanity.com/paper/2107.00296/) (2021)
- [On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective](https://mlsanity.com/paper/2206.06854/) (2022)
- [Sum-of-Parts: Self-Attributing Neural Networks with End-to-End Learning of Feature Groups](https://mlsanity.com/paper/2310.16316/) (2023)
- [Benchmarking Segmentation Models with Mask-Preserved Attribute Editing](https://mlsanity.com/paper/2403.01231/) (2024)
- [Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detection](https://mlsanity.com/paper/2504.07060/) (2025)

## Abstract (arXiv)

The problem of counterfactual visual explanations is considered. A new family of discriminant explanations is introduced. These produce heatmaps that attribute high scores to image regions informative of a classifier prediction but not of a counter class. They connect attributive explanations, which are based on a single heat map, to counterfactual explanations, which account for both predicted class and counter class. The latter are shown to be computable by combination of two discriminant explanations, with reversed class pairs. It is argued that self-awareness, namely the ability to produce classification confidence scores, is important for the computation of discriminant explanations, which seek to identify regions where it is easy to discriminate between prediction and counter class. This suggests the computation of discriminant explanations by the combination of three attribution maps. The resulting counterfactual explanations are optimization free and thus much faster than previous methods. To address the difficulty of their evaluation, a proxy task and set of quantitative metrics are also proposed. Experiments under this protocol show that the proposed counterfactual explanations outperform the state of the art while achieving much higher speeds, for popular networks. In a human-learning machine teaching experiment, they are also shown to improve mean student accuracy from chance level to 95%.