IOMatch: Simplifying Open-Set Semi-Supervised Learning with Joint Inliers and Outliers Utilization

TL;DR

IOMatch introduces a joint utilization approach for inliers and outliers in open-set semi-supervised learning, improving performance by avoiding unreliable outlier filtering and leveraging all unlabeled data effectively.

Contribution

The paper proposes a novel framework that jointly utilizes inliers and outliers with a multi-binary classifier, simplifying open-set SSL and enhancing accuracy without explicit outlier detection.

Findings

Significantly outperforms baseline methods on benchmark datasets.

Effectively leverages all unlabeled data, including outliers.

Simplifies open-set SSL with a unified classification approach.

Abstract

Semi-supervised learning (SSL) aims to leverage massive unlabeled data when labels are expensive to obtain. Unfortunately, in many real-world applications, the collected unlabeled data will inevitably contain unseen-class outliers not belonging to any of the labeled classes. To deal with the challenging open-set SSL task, the mainstream methods tend to first detect outliers and then filter them out. However, we observe a surprising fact that such approach could result in more severe performance degradation when labels are extremely scarce, as the unreliable outlier detector may wrongly exclude a considerable portion of valuable inliers. To tackle with this issue, we introduce a novel open-set SSL framework, IOMatch, which can jointly utilize inliers and outliers, even when it is difficult to distinguish exactly between them. Specifically, we propose to employ a multi-binary classifier in combination with the standard closed-set classifier for producing unified open-set classification targets, which regard all outliers as a single new class. By adopting these targets as open-set pseudo-labels, we optimize an open-set classifier with all unlabeled samples including both inliers and outliers. Extensive experiments have shown that IOMatch significantly outperforms the baseline methods across different benchmark datasets and different settings despite its remarkable simplicity. Our code and models are available at https://github.com/nukezil/IOMatch.