.png){kind=icon}
返回
Improving Model Robustness With Frequency Component Modification and Mixing
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2024.3510923.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep neural networks are sensitive to distribution shifts, such as common corruption and adversarial examples, which occur across various frequency spectra. Numerous studies have been conducted to improve model robustness in the frequency domain. However, research that simultaneously addresses safety metrics, such as corruption, adversaries, consistency, and calibration, is lacking. This study proposes methods named Frequency Component Modification (FCM) and Frequency Component Modification and Mixing (FCMM) to address this gap, as data augmentation techniques in convolutional neural networks (CNNs) for image data. Drawing inspiration from the human vision system's robustness and frequency spectrum distribution, FCM is successfully developed to introduce larger perturbations to high-frequency components while applying smaller variations to low-frequency components. In addition, FCMM mixes the images generated by FCM, providing diversity at low frequencies and improving the model's robustness against low-frequency changes. Experimental results demonstrate that FCMM achieves a 1.4%p reduction in mean corruption error (mCE) on both CIFAR-10-C and CIFAR-100-C, and 1.3%p on ImageNet-C compared to PixMix, which uses additional data. Moreover, when combined with DeepAugment (DA), the leading state-of-the-art (SOTA) method in corruption robustness that requires additional networks for augmentations, FCMM achieves an mCE of 57.2% on ImageNet-C, improving upon DA's standalone performance of 62.0% mCE. These results demonstrate FCMM's superior performance in corruption robustness, while also showing improvements in other safety metrics, such as adversarial robustness, consistency, and calibration.
Keyword:
Robustness
Discrete Fourier transforms
Frequency-domain analysis
Perturbation methods
Training
High frequency
Data augmentation
Convolutional neural networks
Standards
Sensitivity
image augmentation
discrete Fourier transforms
convolutional neural networks
image classification
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
.png){kind=icon}
Role of interfacial phenomena in the behavior of alumina-supported palladium crystallites in oxygen
PREAI
分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏Effects of intravenous calcium on release of serotonin into jejunal lumen and portal circulation
PREAI
分享收藏
查看更多内容