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

02/08/2017
by   Mateusz Kozinski, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/05/2016

Semi-Supervised Learning with Generative Adversarial Networks

We extend Generative Adversarial Networks (GANs) to the semi-supervised ...
research
02/04/2020

Introduction to quasi-open set semi-supervised learning for big data analytics

State-of-the-art performance and low system complexity has made deep-lea...
research
03/27/2017

Mastering Sketching: Adversarial Augmentation for Structured Prediction

We present an integral framework for training sketch simplification netw...
research
02/12/2021

Uncertainty-Aware Semi-supervised Method using Large Unlabelled and Limited Labeled COVID-19 Data

The new coronavirus has caused more than 1 million deaths and continues ...
research
10/02/2018

Semi-supervised Text Regression with Conditional Generative Adversarial Networks

Enormous online textual information provides intriguing opportunities fo...
research
11/05/2019

GAN-enhanced Conditional Echocardiogram Generation

Echocardiography (echo) is a common means of evaluating cardiac conditio...
research
03/07/2019

Adversarial Mixup Resynthesizers

In this paper, we explore new approaches to combining information encode...

Please sign up or login with your details

Forgot password? Click here to reset