# Human-Understandable Decision Making for Visual Recognition

arXiv: https://arxiv.org/abs/2103.03429 · HTML: https://mlsanity.com/paper/2103.03429/

## Key facts

- Cited by 2 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 5 Mar 2021.

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

- ["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)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [Interpretation of Neural Networks is Fragile](https://mlsanity.com/paper/1710.10547/) (2017)
- [Challenges in Representation Learning: A report on three machine learning contests](https://mlsanity.com/paper/1307.0414/) (2013)
- [Interpretable Convolutional Neural Networks](https://mlsanity.com/paper/1710.00935/) (2017)
- [Generating Visual Explanations](https://mlsanity.com/paper/1603.08507/) (2016)
- [Building machines that adapt and compute like brains](https://mlsanity.com/paper/1711.04203/) (2017)
- [The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations](https://mlsanity.com/paper/1907.09294/) (2019)
- [Interpretable and Accurate Fine-grained Recognition via Region Grouping](https://mlsanity.com/paper/2005.10411/) (2020)
- [The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification](https://mlsanity.com/paper/2002.04264/) (2020)
- [Improving Interpretability of Deep Neural Networks with Semantic Information](https://mlsanity.com/paper/1703.04096/) (2017)
- ["Why did you do that?": Explaining black box models with Inductive Synthesis](https://mlsanity.com/paper/1904.09273/) (2019)

## Built on by (most cited first, 2 of 2)

- [PARTICUL: Part Identification with Confidence measure using Unsupervised Learning](https://mlsanity.com/paper/2206.13304/) (2022)
- [FM-ReID: Selective Competitive Token Routing for Object Re-Identification](https://mlsanity.com/paper/2609.36560/) (2026)

## Abstract (arXiv)

The widespread use of deep neural networks has achieved substantial success in many tasks. However, there still exists a huge gap between the operating mechanism of deep learning models and human-understandable decision making, so that humans cannot fully trust the predictions made by these models. To date, little work has been done on how to align the behaviors of deep learning models with human perception in order to train a human-understandable model. To fill this gap, we propose a new framework to train a deep neural network by incorporating the prior of human perception into the model learning process. Our proposed model mimics the process of perceiving conceptual parts from images and assessing their relative contributions towards the final recognition. The effectiveness of our proposed model is evaluated on two classical visual recognition tasks. The experimental results and analysis confirm our model is able to provide interpretable explanations for its predictions, but also maintain competitive recognition accuracy.