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%.
@article{arxiv.2302.14483,
title = {RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Data},
author = {Sangwoo Mo and Jong-Chyi Su and Chih-Yao Ma and Mido Assran and Ishan Misra and Licheng Yu and Sean Bell},
journal= {arXiv preprint arXiv:2302.14483},
year = {2023}
}