An Adversarial Regularisation for Semi-Supervised Training of Structured Output Neural Networks

Abstract

We propose a method for semi-supervised training of structured-output neural networks. Inspired by the framework of Generative Adversarial Networks (GAN), we train a discriminator network to capture the notion of a quality of network output. To this end, we leverage the qualitative difference between outputs obtained on the labelled training data and unannotated data. We then use the discriminator as a source of error signal for unlabelled data. This effectively boosts the performance of a network on a held out test set. Initial experiments in image segmentation demonstrate that the proposed framework enables achieving the same network performance as in a fully supervised scenario, while using two times less annotations.

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Improved Techniques for Training GANs
• Energy-based Generative Adversarial Network
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Adversarial Feature Learning
• Adversarially Learned Inference
• Learning Deconvolution Network for Semantic Segmentation
• Unsupervised Visual Representation Learning by Context Prediction

Cited by in corpus (4)

• Machine Learning with Membership Privacy using Adversarial Regularization
• Student Becoming the Master: Knowledge Amalgamation for Joint Scene Parsing, Depth Estimation, and More
• Privacy Inference Attacks and Defenses in Cloud-based Deep Neural Network: A Survey
• Discriminative Consistent Domain Generation for Semi-supervised Learning