Semi-supervised learning aims to train a model using limited labels. State-of-the-art semi-supervised methods for image classification such as PAWS rely on self-supervised representations learned with large-scale unlabeled but curated data. However, PAWS is often less effective when using real-world unlabeled data that is uncurated, e.g., contains out-of-class data. We propose RoPAWS, a robust extension of PAWS that can work with real-world unlabeled data. We first reinterpret PAWS as a generative classifier that models densities using kernel density estimation. From this probabilistic perspective, we calibrate its prediction based on the densities of labeled and unlabeled data, which leads to a simple closed-form solution from the Bayes' rule. We demonstrate that RoPAWS significantly improves PAWS for uncurated Semi-iNat by +5.3% and curated ImageNet by +0.4%.

我们提出了RoPAWS，它是PAWS的强大扩展，可以使用真实世界未标记的数据。从概率角度出发，我们基于标记和未标记数据的密度进行预测，引入了校准，从而得到了一个不错的结果。我们证明，RoPAWS 对于uncurated Semi-iNat和 curated ImageNet都有明显的提高。

RoPAWS：鲁棒的半监督表征学习从未筛选的数据中