WSAM: Visual Explanations from Style Augmentation as Adversarial Attacker and Their Influence in Image Classification
Not on the map. Why?
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.
Key facts. Cited by 1 paper 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
28 of 31 references.
References · 28
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
- 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
- 2017Axiomatic Attribution for Deep Networkscited by 3,384
- 2016Wide Residual Networkscited by 3,070
- 2015Learning Deep Features for Discriminative Localizationcited by 2,436
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
- 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
- 2013Visualizing and Understanding Convolutional Networkscited by 2,290
- 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
- 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,512
- 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
- 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
16 more
- 2018Sanity Checks for Saliency Mapscited by 1,156
- 2018Explaining Explanations: An Overview of Interpretability of Machine Learningcited by 508
- 2015A Neural Algorithm of Artistic Stylecited by 483
- 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 455
- 2017Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesiscited by 215
- 2017Neural Style Transfer: A Reviewcited by 199
- 2017Exploring the structure of a real-time, arbitrary neural artistic stylization networkcited by 89
- 2018Style Augmentation: Data Augmentation via Style Randomizationcited by 79
- 2019Data Augmentation Using GANscited by 58
- 2018Learning Linear Transformations for Fast Arbitrary Style Transfercited by 48
- 2020SpinalNet: Deep Neural Network with Gradual Inputcited by 40
- 2019STaDA: Style Transfer as Data Augmentationcited by 21
- 2015Stacked What-Where Auto-encoderscited by 20
- 2017Analysis and Optimization of Convolutional Neural Network Architecturescited by 7
- 2019Restyling Data: Application to Unsupervised Domain Adaptationcited by 2
- 2019Intensity augmentation for domain transfer of whole breast segmentation in MRIcited by 1
Built on by
Citing papers per year: 2024: 1.
1 paper.