# Knowledge-Aware Neuron Interpretation for Scene Classification

arXiv: https://arxiv.org/abs/2401.15820 · HTML: https://mlsanity.com/paper/2401.15820/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 28 references that are in the map.
- First posted on arXiv 29 Jan 2024.

## Builds on (most cited first, 11 of 11)

- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Explaining NonLinear Classification Decisions with Deep Taylor Decomposition](https://mlsanity.com/paper/1512.02479/) (2015)
- [On Completeness-aware Concept-Based Explanations in Deep Neural Networks](https://mlsanity.com/paper/1910.07969/) (2019)
- [Compositional Explanations of Neurons](https://mlsanity.com/paper/2006.14032/) (2020)
- [CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks](https://mlsanity.com/paper/2204.10965/) (2022)
- [Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition under Occlusion](https://mlsanity.com/paper/2006.15538/) (2020)
- [A Peek Into the Reasoning of Neural Networks: Interpreting with Structural Visual Concepts](https://mlsanity.com/paper/2105.00290/) (2021)
- [ProjE: Embedding Projection for Knowledge Graph Completion](https://mlsanity.com/paper/1611.05425/) (2016)
- [Knowledge-based Transfer Learning Explanation](https://mlsanity.com/paper/1807.08372/) (2018)
- [Interpreting Face Inference Models using Hierarchical Network Dissection](https://mlsanity.com/paper/2108.10360/) (2021)

## Abstract (arXiv)

Although neural models have achieved remarkable performance, they still encounter doubts due to the intransparency. To this end, model prediction explanation is attracting more and more attentions. However, current methods rarely incorporate external knowledge and still suffer from three limitations: (1) Neglecting concept completeness. Merely selecting concepts may not sufficient for prediction. (2) Lacking concept fusion. Failure to merge semantically-equivalent concepts. (3) Difficult in manipulating model behavior. Lack of verification for explanation on original model. To address these issues, we propose a novel knowledge-aware neuron interpretation framework to explain model predictions for image scene classification. Specifically, for concept completeness, we present core concepts of a scene based on knowledge graph, ConceptNet, to gauge the completeness of concepts. Our method, incorporating complete concepts, effectively provides better prediction explanations compared to baselines. Furthermore, for concept fusion, we introduce a knowledge graph-based method known as Concept Filtering, which produces over 23% point gain on neuron behaviors for neuron interpretation. At last, we propose Model Manipulation, which aims to study whether the core concepts based on ConceptNet could be employed to manipulate model behavior. The results show that core concepts can effectively improve the performance of original model by over 26%.