# Towards interpreting computer vision based on transformation invariant optimization

arXiv: https://arxiv.org/abs/2106.09982 · HTML: https://mlsanity.com/paper/2106.09982/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 24 references that are in the map.
- First posted on arXiv 18 Jun 2021.

## Builds on (most cited first, 12 of 12)

- [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)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Understanding Neural Networks Through Deep Visualization](https://mlsanity.com/paper/1506.06579/) (2015)
- [AdvHat: Real-world adversarial attack on ArcFace Face ID system](https://mlsanity.com/paper/1908.08705/) (2019)
- [Robust Physical-World Attacks on Deep Learning Models](https://mlsanity.com/paper/1707.08945/) (2017)
- [Understanding Adversarial Examples from the Mutual Influence of Images and Perturbations](https://mlsanity.com/paper/2007.06189/) (2020)
- [Fooling a Real Car with Adversarial Traffic Signs](https://mlsanity.com/paper/1907.00374/) (2019)
- [The Definitions of Interpretability and Learning of Interpretable Models](https://mlsanity.com/paper/2105.14171/) (2021)

## Abstract (arXiv)

Interpreting how does deep neural networks (DNNs) make predictions is a vital field in artificial intelligence, which hinders wide applications of DNNs. Visualization of learned representations helps we humans understand the vision of DNNs. In this work, visualized images that can activate the neural network to the target classes are generated by back-propagation method. Here, rotation and scaling operations are applied to introduce the transformation invariance in the image generating process, which we find a significant improvement on visualization effect. Finally, we show some cases that such method can help us to gain insight into neural networks.