FAGC:Feature Augmentation on Geodesic Curve in the Pre-Shape Space
This is an incremental improvement for data augmentation in small-sample scenarios, addressing information loss in existing methods.
The paper tackles the problem of limited training data in deep learning by proposing FAGC, a feature augmentation method on geodesic curves in pre-shape space, which significantly improves performance in small-sample tasks.
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.