# Explaining Neural Networks Semantically and Quantitatively

arXiv: https://arxiv.org/abs/1812.07169 · HTML: https://mlsanity.com/paper/1812.07169/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Dec 2018.

## Built on by (most cited first, 20 of 20)

- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts](https://mlsanity.com/paper/2105.07190/) (2021)
- [FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods](https://mlsanity.com/paper/2308.06248/) (2023)
- [HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks](https://mlsanity.com/paper/2102.02515/) (2021)
- [DISSECT: Disentangled Simultaneous Explanations via Concept Traversals](https://mlsanity.com/paper/2105.15164/) (2021)
- [Explainable Person Re-Identification with Attribute-guided Metric Distillation](https://mlsanity.com/paper/2103.01451/) (2021)
- [Understanding and Enhancing Robustness of Concept-based Models](https://mlsanity.com/paper/2211.16080/) (2022)
- [Concept Embedding Analysis: A Review](https://mlsanity.com/paper/2203.13909/) (2022)
- [Aerial-Ground Person Re-ID](https://mlsanity.com/paper/2303.08597/) (2023)
- [Comprehensible Convolutional Neural Networks via Guided Concept Learning](https://mlsanity.com/paper/2101.03919/) (2021)
- [Benchmarking the Attribution Quality of Vision Models](https://mlsanity.com/paper/2407.11910/) (2024)
- [Deeply Explain CNN via Hierarchical Decomposition](https://mlsanity.com/paper/2201.09205/) (2022)
- [A Large-Scale Empirical Study on Improving the Fairness of Image Classification Models](https://mlsanity.com/paper/2401.03695/) (2024)
- [A Comprehensive Survey on the Risks and Limitations of Concept-based Models](https://mlsanity.com/paper/2506.04237/) (2025)
- [E Pluribus Unum Interpretable Convolutional Neural Networks](https://mlsanity.com/paper/2208.05369/) (2022)
- [A Self-explaining Neural Architecture for Generalizable Concept Learning](https://mlsanity.com/paper/2405.00349/) (2024)
- [Improving Network Interpretability via Explanation Consistency Evaluation](https://mlsanity.com/paper/2408.04600/) (2024)
- [Towards Fully Interpretable Deep Neural Networks: Are We There Yet?](https://mlsanity.com/paper/2106.13164/) (2021)
- [Attention-based Dynamic Subspace Learners for Medical Image Analysis](https://mlsanity.com/paper/2206.09068/) (2022)
- [Revisiting the Role of Texture in 3D Person Re-identification](https://mlsanity.com/paper/2410.00348/) (2024)

## Abstract (arXiv)

This paper presents a method to explain the knowledge encoded in a convolutional neural network (CNN) quantitatively and semantically. The analysis of the specific rationale of each prediction made by the CNN presents a key issue of understanding neural networks, but it is also of significant practical values in certain applications. In this study, we propose to distill knowledge from the CNN into an explainable additive model, so that we can use the explainable model to provide a quantitative explanation for the CNN prediction. We analyze the typical bias-interpreting problem of the explainable model and develop prior losses to guide the learning of the explainable additive model. Experimental results have demonstrated the effectiveness of our method.