WSAM: Visual Explanations from Style Augmentation as Adversarial Attacker and Their Influence in Image Classification
This addresses the robustness of image classification models to style variations, but it appears incremental as it builds on existing style augmentation methods.
The paper tackled the problem of convolutional neural networks being biased towards textures over shapes by introducing a style augmentation algorithm using stochastic sampling and noise addition, which achieved state-of-the-art performance on the STL-10 dataset.
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.