RankMatch: A Novel Approach to Semi-Supervised Label Distribution Learning Leveraging Inter-label Correlations
Abstract
This paper introduces RankMatch, an innovative approach for Semi-Supervised Label Distribution Learning (SSLDL). Addressing the challenge of limited labeled data, RankMatch effectively utilizes a small number of labeled examples in conjunction with a larger quantity of unlabeled data, reducing the need for extensive manual labeling in Deep Neural Network (DNN) applications. Specifically, RankMatch introduces an ensemble learning-inspired averaging strategy that creates a pseudo-label distribution from multiple weakly augmented images. This not only stabilizes predictions but also enhances the model's robustness. Beyond this, RankMatch integrates a pairwise relevance ranking (PRR) loss, capturing the complex inter-label correlations and ensuring that the predicted label distributions align with the ground truth. We establish a theoretical generalization bound for RankMatch, and through extensive experiments, demonstrate its superiority in performance against existing SSLDL methods.
Keywords
Cite
@article{arxiv.2312.06343,
title = {RankMatch: A Novel Approach to Semi-Supervised Label Distribution Learning Leveraging Inter-label Correlations},
author = {Kouzhiqiang Yucheng Xie and Jing Wang and Yuheng Jia and Boyu Shi and Xin Geng},
journal= {arXiv preprint arXiv:2312.06343},
year = {2023}
}