<ul><li>The study introduces FICAug, a feature-to-image data augmentation framework designed to improve model generalization under limited data conditions.</li><li>FICAug operates in the feature space, where original data are clustered and synthetic data is generated through Gaussian sampling.</li><li>These synthetic features are then projected back into the image domain using a generative neural network.</li><li>Experimental results demonstrate that FICAug significantly improves classification accuracy, achieving a cross-validation accuracy of 84.09% in the feature space and 88.63% when training a ResNet-18 model on the reconstructed images.</li></ul>

Feature-to-Image Data Augmentation: Improving Model Feature Extraction with Cluster-Guided Synthetic Samples

Discover more