Invariance encoding in sliced-Wasserstein space for image classification with limited training data.

ABSTRACT: Deep convolutional neural networks (CNNs) are broadly considered to be state-of-the-art generic end-to-end image classification systems. However, they are known to underperform when training data are limited and thus require data augmentation strategies that render the method computationally expensive and not always effective. Rather than using a data augmentation strategy to encode invariances as typically done in machine learning, here we propose to mathematically augment a nearest subspace classification model in sliced-Wasserstein space by exploiting certain mathematical properties of the Radon Cumulative Distribution Transform (R-CDT), a recently introduced image transform. We demonstrate that for a particular type of learning problem, our mathematical solution has advantages over dat

SUBMITTER: Shifat-E-Rabbi M 

PROVIDER: S-EPMC9879373 | biostudies-literature | 2023 May

REPOSITORIES: biostudies-literature