Self Training with Ensemble of Teacher Models

TL;DR

This paper proposes an ensemble-based self-training method for semi-supervised learning that improves model accuracy and calibration, especially when unlabeled data contains out-of-distribution samples.

Contribution

It introduces a novel ensemble approach for self-training that mitigates calibration loss and enhances robustness in semi-supervised classification tasks.

Findings

Improved model accuracy over vanilla self-training methods

Enhanced calibration of the trained models

Effective handling of out-of-distribution unlabeled data

Abstract

In order to train robust deep learning models, large amounts of labelled data is required. However, in the absence of such large repositories of labelled data, unlabeled data can be exploited for the same. Semi-Supervised learning aims to utilize such unlabeled data for training classification models. Recent progress of self-training based approaches have shown promise in this area, which leads to this study where we utilize an ensemble approach for the same. A by-product of any semi-supervised approach may be loss of calibration of the trained model especially in scenarios where unlabeled data may contain out-of-distribution samples, which leads to this investigation on how to adapt to such effects. Our proposed algorithm carefully avoids common pitfalls in utilizing unlabeled data and leads to a more accurate and calibrated supervised model compared to vanilla self-training based student-teacher algorithms. We perform several experiments on the popular STL-10 database followed by an extensive analysis of our approach and study its effects on model accuracy and calibration.