Improving Open-Set Semi-Supervised Learning with Self-Supervision

TL;DR

This paper introduces a novel open-set semi-supervised learning framework that leverages self-supervision and energy-based scoring to effectively utilize all unlabeled data, achieving state-of-the-art results on benchmark datasets.

Contribution

The proposed method uniquely combines self-supervision with energy-based recognition to improve open-set semi-supervised learning performance.

Findings

Achieves state-of-the-art accuracy on benchmark datasets.

Effectively recognizes out-of-distribution data.

Utilizes all unlabeled data for improved learning.

Abstract

Open-set semi-supervised learning (OSSL) embodies a practical scenario within semi-supervised learning, wherein the unlabeled training set encompasses classes absent from the labeled set. Many existing OSSL methods assume that these out-of-distribution data are harmful and put effort into excluding data belonging to unknown classes from the training objective. In contrast, we propose an OSSL framework that facilitates learning from all unlabeled data through self-supervision. Additionally, we utilize an energy-based score to accurately recognize data belonging to the known classes, making our method well-suited for handling uncurated data in deployment. We show through extensive experimental evaluations that our method yields state-of-the-art results on many of the evaluated benchmark problems in terms of closed-set accuracy and open-set recognition when compared with existing methods for OSSL. Our code is available at https://github.com/walline/ssl-tf2-sefoss.