<ul><li>Deep learning models with a large number of parameters have achieved exceptional performance, thanks to effective regularization techniques like data augmentation.</li><li>While data augmentation is widely used in classification tasks, its application in regression problems has been less explored.</li><li>A novel approach called Curvature-Enhanced Manifold Sampling (CEMS) is introduced for regression tasks, which leverages second-order data manifold representation for efficient sampling.</li><li>CEMS shows superior performance in various datasets and scenarios, with minimal computational overhead, as demonstrated through evaluations and comparisons with existing methods.</li></ul>

Curvature Enhanced Data Augmentation for Regression

Discover more