FAAGC: Feature Augmentation on Adaptive Geodesic Curve Based on the shape space theory
This addresses data scarcity issues for domains relying on deep learning, though it appears incremental as it builds on shape space theory.
The paper tackles the problem of limited data in deep learning by proposing the FAAGC method for feature augmentation in pre-shape space, which improves classification accuracy under data-scarce conditions as shown in experiments.
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.