Semi-supervised Learning via Conditional Rotation Angle Estimation

TL;DR

This paper introduces CRAE, a semi-supervised learning method that combines self-supervised rotation angle prediction with class-conditioned modules, achieving state-of-the-art results by effectively utilizing unlabeled data.

Contribution

The paper proposes a novel semi-supervised learning framework, CRAE, that couples self-supervised rotation angle prediction with class conditioning, enhancing performance over existing methods.

Findings

CRAE outperforms existing semi-supervised learning methods.

Extensions to CRAE further improve its performance.

CRAE achieves state-of-the-art results in semi-supervised learning benchmarks.

Abstract

Self-supervised learning (SlfSL), aiming at learning feature representations through ingeniously designed pretext tasks without human annotation, has achieved compelling progress in the past few years. Very recently, SlfSL has also been identified as a promising solution for semi-supervised learning (SemSL) since it offers a new paradigm to utilize unlabeled data. This work further explores this direction by proposing to couple SlfSL with SemSL. Our insight is that the prediction target in SemSL can be modeled as the latent factor in the predictor for the SlfSL target. Marginalizing over the latent factor naturally derives a new formulation which marries the prediction targets of these two learning processes. By implementing this idea through a simple-but-effective SlfSL approach -- rotation angle prediction, we create a new SemSL approach called Conditional Rotation Angle Estimation (CRAE). Specifically, CRAE is featured by adopting a module which predicts the image rotation angle conditioned on the candidate image class. Through experimental evaluation, we show that CRAE achieves superior performance over the other existing ways of combining SlfSL and SemSL. To further boost CRAE, we propose two extensions to strengthen the coupling between SemSL target and SlfSL target in basic CRAE. We show that this leads to an improved CRAE method which can achieve the state-of-the-art SemSL performance.