FAGC:Feature Augmentation on Geodesic Curve in the Pre-Shape Space

TL;DR

FAGC introduces a novel data augmentation technique that constructs geodesic curves in pre-shape space to generate new features, significantly enhancing model performance in small-sample scenarios.

Contribution

The paper proposes a new feature augmentation method using geodesic curves in pre-shape space, addressing information loss issues in existing methods for small-sample learning.

Findings

FAGC improves deep learning performance on small datasets.

The method is versatile across different models.

Experimental results show significant accuracy gains.

Abstract

Due to the constraints on model performance imposed by the size of the training data, data augmentation has become an essential technique in deep learning. However, most existing data augmentation methods are affected by information loss and perform poorly in small-sample scenarios, which limits their application. To overcome the limitation, we propose a Feature Augmentation method on Geodesic Curve in the pre-shape space, called the FAGC. First, a pre-trained neural network model is employed to extract features from the input images. Then, the image features as a vector is projected into the pre-shape space by removing its position and scale information. In the pre-shape space, an optimal Geodesic curve is constructed to fit the feature vectors. Finally, new feature vectors are generated for model learning by interpolating along the constructed Geodesic curve. We conducted extensive experiments to demonstrate the effectiveness and versatility of the FAGC. The results demonstrate that applying the FAGC to deep learning or machine learning methods can significantly improve their performance in small-sample tasks.