Deep learning is pushing the state-of-the-art in many computer vision applications. However, it relies on large annotated data repositories, and capturing the unconstrained nature of the real-world data is yet to be solved. Semi-supervised learning (SSL) complements the annotated training data with a large corpus of unlabeled data to reduce annotation cost. The standard SSL approach assumes unlabeled data are from the same distribution as annotated data. Recently, ORCA [9] introduce a more realistic SSL problem, called open-world SSL, by assuming that the unannotated data might contain samples from unknown classes. This work proposes a novel approach to tackle SSL in open-world setting, where we simultaneously learn to classify known and unknown classes. At the core of our method, we utilize sample uncertainty and incorporate prior knowledge about class distribution to generate reliable pseudo-labels for unlabeled data belonging to both known and unknown classes. Our extensive experimentation showcases the effectiveness of our approach on several benchmark datasets, where it substantially outperforms the existing state-of-the-art on seven diverse datasets including CIFAR-100 (17.6%), ImageNet-100 (5.7%), and Tiny ImageNet (9.9%).

本文提出一种基于伪标签的半监督学习方法，能够处理open-world SSL问题，并通过样本不确定性和类别分布先验知识等手段，为已知和未知类别的未标记数据生成可靠的类别分布感知型伪标签。该方法在多种常用数据集上表现良好，特别是在CIFAR-100，ImageNet-100和Tiny ImageNet数据集上的表现显著优于现有的最先进技术。

朝着真实的半监督学习