.png){kind=icon}
返回
Augmentation invariant manifold learning
.png){kind=icon}
PRE
AI
DOI：10.1093/jrsssb/qkaf003.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Data augmentation is a widely used technique and an essential ingredient in the recent advance in self-supervised representation learning. By preserving the similarity between augmented data, the resulting data representation can improve various downstream analyses and achieve state-of-the-art performance in many applications. Despite the empirical effectiveness, most existing methods lack theoretical understanding under a general nonlinear setting. To fill this gap, we develop a statistical framework on a low-dimensional product manifold to model the data augmentation transformation. Under this framework, we introduce a new representation learning method called augmentation invariant manifold learning and design a computationally efficient algorithm by reformulating it as a stochastic optimization problem. Compared with existing self-supervised methods, the new method simultaneously exploits the manifold's geometric structure and invariant property of augmented data and has an explicit theoretical guarantee. Our theoretical investigation characterizes the role of data augmentation in the proposed method and reveals why and how the data representation learned from augmented data can improve the k-nearest neighbour classifier in the downstream analysis, showing that a more complex data augmentation leads to more improvement in downstream analysis. Finally, numerical experiments on simulated and real data sets are presented to demonstrate the merit of the proposed method.
Keyword:
data augmentation
deep representation learning
manifold learning
k-nearest neighbour
self-supervised learning
期刊
J
IF:
3.6
论文数:
1.5K
被引数:
3.2W
机构
引用论文
Principal manifolds and nonlinear dimensionality reduction via tangent space alignment基于切线空间对齐的主流形和非线性降维
OAAI
OAAI分享收藏Multimodal Data Fusion: An Overview of Methods, Challenges, and Prospects多模态数据融合: 方法、挑战与展望综述.png)
PROCEEDINGS OF THE IEEE
OAAI
PROCEEDINGS OF THE IEEEIF25.9
OAAI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
查看更多内容