# Gradient-Based Interpretability Methods and Binarized Neural Networks

arXiv: https://arxiv.org/abs/2106.12569 · HTML: https://mlsanity.com/paper/2106.12569/

## Key facts

- Cited by 1 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 23 Jun 2021.

## 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)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Towards Accurate Binary Convolutional Neural Network](https://mlsanity.com/paper/1711.11294/) (2017)
- [Training Binary Neural Networks with Real-to-Binary Convolutions](https://mlsanity.com/paper/2003.11535/) (2020)
- [Defensive Quantization: When Efficiency Meets Robustness](https://mlsanity.com/paper/1904.08444/) (2019)
- [MeliusNet: Can Binary Neural Networks Achieve MobileNet-level Accuracy?](https://mlsanity.com/paper/2001.05936/) (2020)
- [Attacking Binarized Neural Networks](https://mlsanity.com/paper/1711.00449/) (2017)
- [Back to Simplicity: How to Train Accurate BNNs from Scratch?](https://mlsanity.com/paper/1906.08637/) (2019)
- [Larq Compute Engine: Design, Benchmark, and Deploy State-of-the-Art Binarized Neural Networks](https://mlsanity.com/paper/2011.09398/) (2020)

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

- [CRITS: Convolutional Rectifier for Interpretable Time Series Classification](https://mlsanity.com/paper/2506.12042/) (2025)

## Abstract (arXiv)

Binarized Neural Networks (BNNs) have the potential to revolutionize the way that deep learning is carried out in edge computing platforms. However, the effectiveness of interpretability methods on these networks has not been assessed. In this paper, we compare the performance of several widely used saliency map-based interpretabilty techniques (Gradient, SmoothGrad and GradCAM), when applied to Binarized or Full Precision Neural Networks (FPNNs). We found that the basic Gradient method produces very similar-looking maps for both types of network. However, SmoothGrad produces significantly noisier maps for BNNs. GradCAM also produces saliency maps which differ between network types, with some of the BNNs having seemingly nonsensical explanations. We comment on possible reasons for these differences in explanations and present it as an example of why interpretability techniques should be tested on a wider range of network types.