Generalizing semi-supervised generative adversarial networks to regression using feature contrasting

Abstract

In this work, we generalize semi-supervised generative adversarial networks (GANs) from classification problems to regression problems. In the last few years, the importance of improving the training of neural networks using semi-supervised training has been demonstrated for classification problems. We present a novel loss function, called feature contrasting, resulting in a discriminator which can distinguish between fake and real data based on feature statistics. This method avoids potential biases and limitations of alternative approaches. The generalization of semi-supervised GANs to the regime of regression problems of opens their use to countless applications as well as providing an avenue for a deeper understanding of how GANs function. We first demonstrate the capabilities of semi-supervised regression GANs on a toy dataset which allows for a detailed understanding of how they operate in various circumstances. This toy dataset is used to provide a theoretical basis of the semi-supervised regression GAN. We then apply the semi-supervised regression GANs to a number of real-world computer vision applications: age estimation, driving steering angle prediction, and crowd counting from single images. We perform extensive tests of what accuracy can be achieved with significantly reduced annotated data. Through the combination of the theoretical example and real-world scenarios, we demonstrate how semi-supervised GANs can be generalized to regression problems.

References in corpus (12)

• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
• Adversarial Examples that Fool both Computer Vision and Time-Limited Humans
• An Application of Deep Neural Networks in the Analysis of Stellar Spectra
• Semi and Weakly Supervised Semantic Segmentation Using Generative Adversarial Network
• Convergence Problems with Generative Adversarial Networks (GANs)
• Semi-supervised Conditional GANs
• State-Space Inference for Non-Linear Latent Force Models with Application to Satellite Orbit Prediction
• Versatile Auxiliary Regressor with Generative Adversarial network (VAR+GAN)

Cited by in corpus (6)

• Fast Parallel Hypertree Decompositions in Logarithmic Recursion Depth
• CNN-based Density Estimation and Crowd Counting: A Survey
• Domain-adaptive Crowd Counting via High-quality Image Translation and Density Reconstruction
• Active Crowd Counting with Limited Supervision
• Optimizing BioTac Simulation for Realistic Tactile Perception
• Mixed Semi-Supervised Generalized-Linear-Regression with Applications to Deep-Learning and Interpolators