OwMatch: Conditional Self-Labeling with Consistency for Open-World Semi-Supervised Learning
This addresses a practical challenge in semi-supervised learning for scenarios with incomplete class labeling, offering a solution to prevent misclassification of unseen classes.
The paper tackles the problem of open-world semi-supervised learning, where unlabeled data includes unseen classes, by proposing OwMatch, a framework combining conditional self-labeling and open-world hierarchical thresholding, resulting in substantial performance improvements across known and unknown classes compared to prior methods.
Semi-supervised learning (SSL) offers a robust framework for harnessing the potential of unannotated data. Traditionally, SSL mandates that all classes possess labeled instances. However, the emergence of open-world SSL (OwSSL) introduces a more practical challenge, wherein unlabeled data may encompass samples from unseen classes. This scenario leads to misclassification of unseen classes as known ones, consequently undermining classification accuracy. To overcome this challenge, this study revisits two methodologies from self-supervised and semi-supervised learning, self-labeling and consistency, tailoring them to address the OwSSL problem. Specifically, we propose an effective framework called OwMatch, combining conditional self-labeling and open-world hierarchical thresholding. Theoretically, we analyze the estimation of class distribution on unlabeled data through rigorous statistical analysis, thus demonstrating that OwMatch can ensure the unbiasedness of the self-label assignment estimator with reliability. Comprehensive empirical analyses demonstrate that our method yields substantial performance enhancements across both known and unknown classes in comparison to previous studies. Code is available at https://github.com/niusj03/OwMatch.