RankMatch: A Novel Approach to Semi-Supervised Label Distribution Learning Leveraging Inter-label Correlations
This addresses the need for reduced manual labeling in deep neural network applications, though it appears incremental as it builds on existing semi-supervised and label distribution learning approaches.
The paper tackles the problem of limited labeled data in semi-supervised label distribution learning by introducing RankMatch, which uses an averaging strategy and pairwise relevance ranking loss to leverage unlabeled data and inter-label correlations, achieving superior performance over existing methods in experiments.
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.