.png){kind=icon}
返回
Are transformer-based models more robust than CNN-based models?
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neunet.2023.12.045.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
As the deployment of artificial intelligence (AI) models in real -world settings grows, their open -environment robustness becomes increasingly critical. This study aims to dissect the robustness of deep learning models, particularly comparing transformer -based models against CNN -based models. We focus on unraveling the sources of robustness from two key perspectives: structural and process robustness. Our findings suggest that transformer -based models generally outperform convolution -based models in robustness across multiple metrics. However, we contend that these metrics may not wholly represent true model robustness, such as the mean of corruption error. To better understand the underpinnings of this robustness advantage, we analyze models through the lens of Fourier transform and game interaction. From our insights, we propose a calibrated evaluation metric for robustness against real -world data, and a blur -based method to enhance robustness performance. Our approach achieves state-of-the-art results, with mCE scores of 2.1% on CIFAR-10-C, 12.4% on CIFAR-100-C, and 24.9% on TinyImageNet-C.
Keyword:
Data augmentation
Model robustness
Deep learning
Image classification
期刊
IF:
6.3
论文数:
8.2K
被引数:
3.0W
机构
引用论文
Inflexibility of mental planning: A characteristic disorder with prefrontal lobe lesions?心理计划的僵化: 前额叶病变的特征性障碍？
PREAI
分享收藏Energy-Efficient Robot Configuration and Motion Planning Using Genetic Algorithm and Particle Swarm Optimization基于遗传算法和粒子群算法的节能机器人配置和运动规划.png)
Energies
OAAI
EnergiesIF0
OAAI分享收藏On the robustness of skeleton detection against adversarial attacks骨架检测对对抗攻击的鲁棒性研究NEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏分享收藏
查看更多内容