Learning by Association - A versatile semi-supervised training method for neural networks

Abstract

In many real-world scenarios, labeled data for a specific machine learning task is costly to obtain. Semi-supervised training methods make use of abundantly available unlabeled data and a smaller number of labeled examples. We propose a new framework for semi-supervised training of deep neural networks inspired by learning in humans. "Associations" are made from embeddings of labeled samples to those of unlabeled ones and back. The optimization schedule encourages correct association cycles that end up at the same class from which the association was started and penalizes wrong associations ending at a different class. The implementation is easy to use and can be added to any existing end-to-end training setup. We demonstrate the capabilities of learning by association on several data sets and show that it can improve performance on classification tasks tremendously by making use of additionally available unlabeled data. In particular, for cases with few labeled data, our training scheme outperforms the current state of the art on SVHN.

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017

References in corpus (2)

• Natural Language Processing (almost) from Scratch
• Going Deeper with Convolutions

Cited by in corpus (13)

• Associative Domain Adaptation
• Semi-Supervised Learning by Label Gradient Alignment
• Unsupervised Learning Facial Parameter Regressor for Action Unit Intensity Estimation via Differentiable Renderer
• Be Consistent! Improving Procedural Text Comprehension using Label Consistency
• Exploiting Contextual Information with Deep Neural Networks
• MUSCLE: Strengthening Semi-Supervised Learning Via Concurrent Unsupervised Learning Using Mutual Information Maximization
• Consistency Regularization with Generative Adversarial Networks for Semi-Supervised Learning
• Towards Robust Pattern Recognition: A Review
• Unsupervised Facial Action Unit Intensity Estimation via Differentiable Optimization
• End-To-End Graph-based Deep Semi-Supervised Learning
• Iterative Self-Learning: Semi-Supervised Improvement to Dataset Volumes and Model Accuracy
• Semi-supervised Learning with Contrastive Predicative Coding
• Smart-Inspect: Micro Scale Localization and Classification of Smartphone Glass Defects for Industrial Automation