Improving Dataset Volumes and Model Accuracy With Semi-Supervised Iterative Self-Learning

摘要

Within this paper, a novel semi-supervised learning technique is introduced based on a simple iterative learning cycle together with learned thresholding techniques and an ensemble decision support system. The state-of-the-art model performance and increased training data volume are demonstrated through the use of unlabeled data when training deeply learned classification models. The methods presented work independently from the model architectures or loss functions, making this approach applicable to a wide range of machine learning and classification tasks. Evaluation of the proposed approach is performed on commonly used datasets when evaluating semi-supervised learning techniques and a number of more challenging image classification datasets (CIFAR-100 and a 200 class subset of ImageNet).