# Towards Human-Understandable Visual Explanations:Imperceptible High-frequency Cues Can Better Be Removed

arXiv: https://arxiv.org/abs/2104.07954 · HTML: https://mlsanity.com/paper/2104.07954/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 32 references that are in the map.
- First posted on arXiv 16 Apr 2021.

## Builds on (most cited first, 21 of 21)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [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)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [MaskGAN: Towards Diverse and Interactive Facial Image Manipulation](https://mlsanity.com/paper/1907.11922/) (2019)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [Leveraging Frequency Analysis for Deep Fake Image Recognition](https://mlsanity.com/paper/2003.08685/) (2020)
- [High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks](https://mlsanity.com/paper/1905.13545/) (2019)
- [Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributions](https://mlsanity.com/paper/2003.01826/) (2020)
- [Global Texture Enhancement for Fake Face Detection in the Wild](https://mlsanity.com/paper/2002.00133/) (2020)
- [Evaluating Weakly Supervised Object Localization Methods Right](https://mlsanity.com/paper/2001.07437/) (2020)
- [Unmasking DeepFakes with simple Features](https://mlsanity.com/paper/1911.00686/) (2019)
- [Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks](https://mlsanity.com/paper/1712.06302/) (2017)
- [A Taxonomy and Library for Visualizing Learned Features in Convolutional Neural Networks](https://mlsanity.com/paper/1606.07757/) (2016)

## Built on by (most cited first, 1 of 1)

- [Quantitative Metrics for Evaluating Explanations of Video DeepFake Detectors](https://mlsanity.com/paper/2210.03683/) (2022)

## Abstract (arXiv)

Explainable AI (XAI) methods focus on explaining what a neural network has learned - in other words, identifying the features that are the most influential to the prediction. In this paper, we call them "distinguishing features". However, whether a human can make sense of the generated explanation also depends on the perceptibility of these features to humans. To make sure an explanation is human-understandable, we argue that the capabilities of humans, constrained by the Human Visual System (HVS) and psychophysics, need to be taken into account. We propose the em human perceptibility principle for XAI, stating that, to generate human-understandable explanations, neural networks should be steered towards focusing on human-understandable cues during training. We conduct a case study regarding the classification of real vs. fake face images, where many of the distinguishing features picked up by standard neural networks turn out not to be perceptible to humans. By applying the proposed principle, a neural network with human-understandable explanations is trained which, in a user study, is shown to better align with human intuition. This is likely to make the AI more trustworthy and opens the door to humans learning from machines. In the case study, we specifically investigate and analyze the behaviour of the human-imperceptible high spatial frequency features in neural networks and XAI methods.