AdvMask: A Sparse Adversarial Attack Based Data Augmentation Method for Image Classification

TL;DR

AdvMask introduces a novel data augmentation technique that uses sparse adversarial attacks to identify and mask key image regions, improving CNN generalization in image classification.

Contribution

This paper presents AdvMask, a new data augmentation method that targets influential image regions based on adversarial attacks, unlike traditional random occlusion methods.

Findings

Outperforms previous augmentation methods on multiple datasets

Enhances CNN robustness by focusing on critical image regions

Improves classification accuracy in testing phase

Abstract

Data augmentation is a widely used technique for enhancing the generalization ability of convolutional neural networks (CNNs) in image classification tasks. Occlusion is a critical factor that affects on the generalization ability of image classification models. In order to generate new samples, existing data augmentation methods based on information deletion simulate occluded samples by randomly removing some areas in the images. However, those methods cannot delete areas of the images according to their structural features of the images. To solve those problems, we propose a novel data augmentation method, AdvMask, for image classification tasks. Instead of randomly removing areas in the images, AdvMask obtains the key points that have the greatest influence on the classification results via an end-to-end sparse adversarial attack module. Therefore, we can find the most sensitive points of the classification results without considering the diversity of various image appearance and shapes of the object of interest. In addition, a data augmentation module is employed to generate structured masks based on the key points, thus forcing the CNN classification models to seek other relevant content when the most discriminative content is hidden. AdvMask can effectively improve the performance of classification models in the testing process. The experimental results on various datasets and CNN models verify that the proposed method outperforms other previous data augmentation methods in image classification tasks.