# Measurably Stronger Explanation Reliability via Model Canonization

arXiv: https://arxiv.org/abs/2202.06621 · HTML: https://mlsanity.com/paper/2202.06621/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 23 references that are in the map.
- First posted on arXiv 14 Feb 2022.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [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)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [Evaluating the visualization of what a Deep Neural Network has learned](https://mlsanity.com/paper/1509.06321/) (2015)
- [Top-down Neural Attention by Excitation Backprop](https://mlsanity.com/paper/1608.00507/) (2016)
- [Not Just a Black Box: Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1605.01713/) (2016)
- [Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruning](https://mlsanity.com/paper/1912.08881/) (2019)
- [Towards Best Practice in Explaining Neural Network Decisions with LRP](https://mlsanity.com/paper/1910.09840/) (2019)
- [Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAy](https://mlsanity.com/paper/2106.13200/) (2021)
- [Breaking Batch Normalization for better explainability of Deep Neural Networks through Layer-wise Relevance Propagation](https://mlsanity.com/paper/2002.11018/) (2020)

## Built on by (most cited first, 6 of 6)

- [Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanations](https://mlsanity.com/paper/2211.11426/) (2022)
- [Optimizing Explanations by Network Canonization and Hyperparameter Search](https://mlsanity.com/paper/2211.17174/) (2022)
- [Efficient and Flexible Neural Network Training through Layer-wise Feedback Propagation](https://mlsanity.com/paper/2308.12053/) (2023)
- [Locally Testing Model Detections for Semantic Global Concepts](https://mlsanity.com/paper/2405.17523/) (2024)
- [GAMER-MRIL identifies Disability-Related Brain Changes in Multiple Sclerosis](https://mlsanity.com/paper/2308.07611/) (2023)
- [Relevance-driven Input Dropout: an Explanation-guided Regularization Technique](https://mlsanity.com/paper/2505.21595/) (2025)

## Abstract (arXiv)

While rule-based attribution methods have proven useful for providing local explanations for Deep Neural Networks, explaining modern and more varied network architectures yields new challenges in generating trustworthy explanations, since the established rule sets might not be sufficient or applicable to novel network structures. As an elegant solution to the above issue, network canonization has recently been introduced. This procedure leverages the implementation-dependency of rule-based attributions and restructures a model into a functionally identical equivalent of alternative design to which established attribution rules can be applied. However, the idea of canonization and its usefulness have so far only been explored qualitatively. In this work, we quantitatively verify the beneficial effects of network canonization to rule-based attributions on VGG-16 and ResNet18 models with BatchNorm layers and thus extend the current best practices for obtaining reliable neural network explanations.