FAAGC: Feature Augmentation on Adaptive Geodesic Curve Based on the shape space theory

TL;DR

This paper introduces FAAGC, a feature augmentation method using geodesic curves in shape space to enhance deep learning performance with limited data.

Contribution

It proposes a novel feature augmentation technique based on geodesic curves in pre-shape space, improving data efficiency in deep learning models.

Findings

Enhances classification accuracy in data-scarce scenarios

Generalizes well across different feature types

Effective in various deep learning applications

Abstract

Deep learning models have been widely applied across various domains and industries. However, many fields still face challenges due to limited and insufficient data. This paper proposes a Feature Augmentation on Adaptive Geodesic Curve (FAAGC) method in the pre-shape space to increase data. In the pre-shape space, objects with identical shapes lie on a great circle. Thus, we project deep model representations into the pre-shape space and construct a geodesic curve, i.e., an arc of a great circle, for each class. Feature augmentation is then performed by sampling along these geodesic paths. Extensive experiments demonstrate that FAAGC improves classification accuracy under data-scarce conditions and generalizes well across various feature types.