Matching Distributions via Optimal Transport for Semi-Supervised Learning

TL;DR

This paper introduces a novel semi-supervised learning method using optimal transport to generate pseudo-labels for unlabeled data, improving CNN training on standard benchmarks.

Contribution

It proposes a new SSL approach that leverages optimal transport to measure similarity between data distributions for pseudo-labeling.

Findings

Outperforms state-of-the-art SSL methods on benchmark datasets.

Demonstrates effectiveness of optimal transport in semi-supervised CNN training.

Provides a unified framework for labeled and unlabeled data integration.

Abstract

Semi-Supervised Learning (SSL) approaches have been an influential framework for the usage of unlabeled data when there is not a sufficient amount of labeled data available over the course of training. SSL methods based on Convolutional Neural Networks (CNNs) have recently provided successful results on standard benchmark tasks such as image classification. In this work, we consider the general setting of SSL problem where the labeled and unlabeled data come from the same underlying probability distribution. We propose a new approach that adopts an Optimal Transport (OT) technique serving as a metric of similarity between discrete empirical probability measures to provide pseudo-labels for the unlabeled data, which can then be used in conjunction with the initial labeled data to train the CNN model in an SSL manner. We have evaluated and compared our proposed method with state-of-the-art SSL algorithms on standard datasets to demonstrate the superiority and effectiveness of our SSL algorithm.