Self Training with Ensemble of Teacher Models
This work addresses the challenge of semi-supervised learning for classification, particularly in handling out-of-distribution samples, but it is incremental as it builds on existing self-training approaches.
The paper tackles the problem of training robust deep learning models with limited labeled data by proposing a self-training algorithm using an ensemble of teacher models, which improves accuracy and calibration compared to vanilla methods, as demonstrated on the STL-10 database.
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.