Iterative Self-Learning: Semi-Supervised Improvement to Dataset Volumes and Model Accuracy
This work addresses the challenge of leveraging unlabeled data for image classification, offering a method that is incremental in nature.
The paper tackles the problem of improving model accuracy and training data volume in semi-supervised learning by introducing an iterative learning cycle with thresholding and ensemble support, achieving state-of-the-art performance on datasets like CIFAR-100 and ImageNet subsets.
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. State-of-the-art model performance and increased training data volume are demonstrated, through the use of unlabelled data when training deeply learned classification models. Evaluation of the proposed approach is performed on commonly used datasets when evaluating semi-supervised learning techniques as well as a number of more challenging image classification datasets (CIFAR-100 and a 200 class subset of ImageNet).