• PDF / 7,257,492 Bytes
• 26 Pages / 439.642 x 666.49 pts Page_size
• 43 Downloads / 198 Views

DOWNLOAD

REPORT

---

Semi-supervised self-growing generative adversarial networks for image recognition Zhiwei Xu1 · Haoqian Wang1,2 · Yi Yang2 Received: 29 March 2020 / Revised: 24 June 2020 / Accepted: 12 August 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020

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 self-generative approach, namely the semisupervised 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. Keywords Semi-supervised learning · Generative adversarial network · Self-growing technique · Image recognition · Face attribute recognition

The work is partially supported by the NSFC fund (61831014),Shenzhen Science, Technology Project under Grant (JSGG20170822154824030,JCYJ20180508152042002) and Shenzhen Innovation Chain and Industry Chain Integration Project under Grant (ZDYBH201900000002).  Haoqian Wang

[email protected]

Extended author information available on the last page of the article.

Multimedia Tools and Applications

1 Introduction In the past decade, we have witnessed the increasing interests in the image recognition problem solved by the deep learning approaches [20, 27, 51], This interest is expanding quickly to many different fields ever since the advent of deep convolution neural networks [16, 20, 27, 51], resulting in many effective approaches in many different computer vision fields [6, 14, 35, 37, 38]. However, despite these exciting progresses, most existing approaches are supervised learning based and largely limited by resorting to huge amounts of data with labels. Labeling these data