# WSAM: Visual Explanations from Style Augmentation as Adversarial Attacker and Their Influence in Image Classification

arXiv: https://arxiv.org/abs/2308.14995 · HTML: https://mlsanity.com/paper/2308.14995/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 31 references that are in the map.
- First posted on arXiv 29 Aug 2023.

## Builds on (most cited first, 28 of 28)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Explaining Explanations: An Overview of Interpretability of Machine Learning](https://mlsanity.com/paper/1806.00069/) (2018)
- [A Neural Algorithm of Artistic Style](https://mlsanity.com/paper/1508.06576/) (2015)
- [Invariant Information Clustering for Unsupervised Image Classification and Segmentation](https://mlsanity.com/paper/1807.06653/) (2018)
- [Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesis](https://mlsanity.com/paper/1701.02096/) (2017)
- [Neural Style Transfer: A Review](https://mlsanity.com/paper/1705.04058/) (2017)
- [Exploring the structure of a real-time, arbitrary neural artistic stylization network](https://mlsanity.com/paper/1705.06830/) (2017)
- [Style Augmentation: Data Augmentation via Style Randomization](https://mlsanity.com/paper/1809.05375/) (2018)
- [Data Augmentation Using GANs](https://mlsanity.com/paper/1904.09135/) (2019)
- [Learning Linear Transformations for Fast Arbitrary Style Transfer](https://mlsanity.com/paper/1808.04537/) (2018)
- [SpinalNet: Deep Neural Network with Gradual Input](https://mlsanity.com/paper/2007.03347/) (2020)
- [STaDA: Style Transfer as Data Augmentation](https://mlsanity.com/paper/1909.01056/) (2019)
- [Stacked What-Where Auto-encoders](https://mlsanity.com/paper/1506.02351/) (2015)
- [Analysis and Optimization of Convolutional Neural Network Architectures](https://mlsanity.com/paper/1707.09725/) (2017)
- [Restyling Data: Application to Unsupervised Domain Adaptation](https://mlsanity.com/paper/1909.10900/) (2019)
- [Intensity augmentation for domain transfer of whole breast segmentation in MRI](https://mlsanity.com/paper/1909.02642/) (2019)

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

- [Context-based Interpretable Spatio-Temporal Graph Convolutional Network for Human Motion Forecasting](https://mlsanity.com/paper/2402.19237/) (2024)

## Abstract (arXiv)

Currently, style augmentation is capturing attention due to convolutional neural networks (CNN) being strongly biased toward recognizing textures rather than shapes. Most existing styling methods either perform a low-fidelity style transfer or a weak style representation in the embedding vector. This paper outlines a style augmentation algorithm using stochastic-based sampling with noise addition to improving randomization on a general linear transformation for style transfer. With our augmentation strategy, all models not only present incredible robustness against image stylizing but also outperform all previous methods and surpass the state-of-the-art performance for the STL-10 dataset. In addition, we present an analysis of the model interpretations under different style variations. At the same time, we compare comprehensive experiments demonstrating the performance when applied to deep neural architectures in training settings.