Matching Distributions via Optimal Transport for Semi-Supervised Learning
This work provides an incremental improvement for researchers and practitioners working on semi-supervised learning, particularly in image classification tasks, by offering a new method for pseudo-label generation.
This paper proposes a semi-supervised learning (SSL) approach that uses Optimal Transport (OT) to generate pseudo-labels for unlabeled data. These pseudo-labels are then combined with initial labeled data to train a Convolutional Neural Network (CNN) model. The method was evaluated against state-of-the-art SSL algorithms on standard datasets, demonstrating superior effectiveness.
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.