.png){kind=icon}
返回
AdvMask: A sparse adversarial attack-based data augmentation method for image classification
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2023.109847.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Data augmentation has been an essential technique for improving the generalization ability of deep neural networks in image classification tasks. However, intensive changes in appearance and different degrees of occlusion in images are the key factors that severely affect the generalization ability of image classification models. Therefore, in order to enhance the generalization performance and robustness of deep models, data augmentation approaches by providing models with more diverse training data in various scenarios are widely applied. Although many existing data augmentation methods simulate occlusion in the augmented images to enhance the generalization of models, these methods randomly delete some areas in images without considering the semantic information of images. In this work, we propose a novel data augmentation method named AdvMask for image classification based on sparse adversarial attack techniques. AdvMask first identifies the key points that have the greatest influence on the classification results via a proposed end-to-end sparse adversarial attack module. During the data augmentation process, AdvMask efficiently generates diverse augmented data with structured occlusions based on the key points. By doing so, AdvMask can force deep models to seek other relevant content while the most discriminative content is hidden. Extensive experimental results on various benchmark datasets and deep models demonstrate that our proposed method can effectively improve the generalization performance of deep models and significantly outperforms previous data augmentation methods. Code for reproducing our results is available at https://github.com/Jackbrocp/AdvMask.
Keyword:
Data augmentation
Image classification
Sparse adversarial attack
Generalization
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7.6
论文数:
1.4W
被引数:
4.5W
机构
引用论文
How Resilient Are Deep Learning Models in Medical Image Analysis? The Case of the Moment-Based Adversarial Attack (Mb-AdA)深度学习模型在医学图像分析中的弹性有多大？基于矩的对抗攻击 (mb-ada) 的案例.png)
BIOMEDICINESOAAI
BIOMEDICINESIF3.9
OAAI分享收藏LONG‐TERM EFFECTS OF A SINGLE DOSE OF ULTRAVIOLET‐B ON ALBINO RABBIT CORNEA‐I. in vivo ANALYSES
PREAI
分享收藏Visual vs internal attention mechanisms in deep neural networks for image classification and object detection用于图像分类和目标检测的深度神经网络视觉vs内部注意机制PATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏
查看更多内容