# Semi-Supervised Self-Growing Generative Adversarial Networks for Image Recognition

## TL;DR

This paper introduces SGGAN, a semi-supervised generative adversarial network that effectively leverages unlabeled data for image recognition, achieving high accuracy with minimal labeled data by novel confidence measurement and classifier generalization techniques.

## Contribution

The paper proposes a semi-supervised self-growing GAN with a new confidence measurement and convolution-block-transformation, improving training stability and performance over standard semi-supervised GANs.

## Key findings

- Achieves comparable accuracy to supervised methods with only 4% labeled facial data.
- Uses Maximum Mean Discrepancy for stable and faster training.
- Effective on benchmark image and facial attribute recognition datasets.

## Abstract

Image recognition is an important topic in computer vision and image processing, and has been mainly addressed by supervised deep learning methods, which need a large set of labeled images to achieve promising performance. However, in most cases, labeled data are expensive or even impossible to obtain, while unlabeled data are readily available from numerous free on-line resources and have been exploited to improve the performance of deep neural networks. To better exploit the power of unlabeled data for image recognition, in this paper, we propose a semi-supervised and generative approach, namely the semi-supervised self-growing generative adversarial network (SGGAN). Label inference is a key step for the success of semi-supervised learning approaches. There are two main problems in label inference: how to measure the confidence of the unlabeled data and how to generalize the classifier. We address these two problems via the generative framework and a novel convolution-block-transformation technique, respectively. To stabilize and speed up the training process of SGGAN, we employ the metric Maximum Mean Discrepancy as the feature matching objective function and achieve larger gain than the standard semi-supervised GANs (SSGANs), narrowing the gap to the supervised methods. Experiments on several benchmark datasets show the effectiveness of the proposed SGGAN on image recognition and facial attribute recognition tasks. By using the training data with only 4% labeled facial attributes, the SGGAN approach can achieve comparable accuracy with leading supervised deep learning methods with all labeled facial attributes.