Iterative Self-Learning: Semi-Supervised Improvement to Dataset Volumes and Model Accuracy

Abstract

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).

References in corpus (8)

• Sequence to Sequence Learning with Neural Networks
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
• Improved Techniques for Training GANs
• Semi-Supervised Learning with Ladder Networks
• Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
• Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation
• Learning by Association - A versatile semi-supervised training method for neural networks
• SaaS: Speed as a Supervisor for Semi-supervised Learning