# Detection Accuracy for Evaluating Compositional Explanations of Units

arXiv: https://arxiv.org/abs/2109.07804 · HTML: https://mlsanity.com/paper/2109.07804/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 41 references that are in the map.
- First posted on arXiv 16 Sep 2021.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Evaluating the visualization of what a Deep Neural Network has learned](https://mlsanity.com/paper/1509.06321/) (2015)
- [Understanding Deep Image Representations by Inverting Them](https://mlsanity.com/paper/1412.0035/) (2014)
- [Generating Videos with Scene Dynamics](https://mlsanity.com/paper/1609.02612/) (2016)
- [Synthesizing the preferred inputs for neurons in neural networks via deep generator networks](https://mlsanity.com/paper/1605.09304/) (2016)
- [Object Detectors Emerge in Deep Scene CNNs](https://mlsanity.com/paper/1412.6856/) (2014)
- [Compositional Explanations of Neurons](https://mlsanity.com/paper/2006.14032/) (2020)
- [Explaining Explanations in AI](https://mlsanity.com/paper/1811.01439/) (2018)
- [Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruning](https://mlsanity.com/paper/1912.08881/) (2019)
- [Towards better understanding of gradient-based attribution methods for Deep Neural Networks](https://mlsanity.com/paper/1711.06104/) (2017)
- [What Do You See? Evaluation of Explainable Artificial Intelligence (XAI) Interpretability through Neural Backdoors](https://mlsanity.com/paper/2009.10639/) (2020)
- [NeuroX: A Toolkit for Analyzing Individual Neurons in Neural Networks](https://mlsanity.com/paper/1812.09359/) (2018)
- [Evaluating Explanation Without Ground Truth in Interpretable Machine Learning](https://mlsanity.com/paper/1907.06831/) (2019)
- [Do semantic parts emerge in Convolutional Neural Networks?](https://mlsanity.com/paper/1607.03738/) (2016)

## Built on by (most cited first, 3 of 3)

- [Towards a fuller understanding of neurons with Clustered Compositional Explanations](https://mlsanity.com/paper/2310.18443/) (2023)
- [Open Vocabulary Compositional Explanations for Neuron Alignment](https://mlsanity.com/paper/2511.20931/) (2025)
- [Guaranteed Optimal Compositional Explanations for Neurons](https://mlsanity.com/paper/2511.20934/) (2025)

## Abstract (arXiv)

The recent success of deep learning models in solving complex problems and in different domains has increased interest in understanding what they learn. Therefore, different approaches have been employed to explain these models, one of which uses human-understandable concepts as explanations. Two examples of methods that use this approach are Network Dissection and Compositional explanations. The former explains units using atomic concepts, while the latter makes explanations more expressive, replacing atomic concepts with logical forms. While intuitively, logical forms are more informative than atomic concepts, it is not clear how to quantify this improvement, and their evaluation is often based on the same metric that is optimized during the search-process and on the usage of hyper-parameters to be tuned. In this paper, we propose to use as evaluation metric the Detection Accuracy, which measures units' consistency of detection of their assigned explanations. We show that this metric (1) evaluates explanations of different lengths effectively, (2) can be used as a stopping criterion for the compositional explanation search, eliminating the explanation length hyper-parameter, and (3) exposes new specialized units whose length 1 explanations are the perceptual abstractions of their longer explanations.