Saved in:
Bibliographic Details
Main Authors: Han, Yuexing, Hu, Gan, Wan, Guanxin, Wang, Bing
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2312.03325
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912572197830656
author Han, Yuexing
Hu, Gan
Wan, Guanxin
Wang, Bing
author_facet Han, Yuexing
Hu, Gan
Wan, Guanxin
Wang, Bing
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2312_03325
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle FAGC:Feature Augmentation on Geodesic Curve in the Pre-Shape Space
Han, Yuexing
Hu, Gan
Wan, Guanxin
Wang, Bing
Computer Vision and Pattern Recognition
Machine Learning
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.
title FAGC:Feature Augmentation on Geodesic Curve in the Pre-Shape Space
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2312.03325