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

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.

arXiv comment13 pages, 11 figures, 8 tables. arXiv admin note: text overlap with arXiv:1606.03498 by other authors

References in corpus (18)

• Empirical Evaluation of Rectified Activations in Convolutional Network
• Semi-Supervised Learning with Deep Generative Models
• Improved Techniques for Training GANs
• Adversarial Feature Learning
• Video Salient Object Detection via Fully Convolutional Networks
• Semi-Supervised Learning with Ladder Networks
• Semi-supervised Sequence Learning
• MMD GAN: Towards Deeper Understanding of Moment Matching Network
• Distributional Smoothing with Virtual Adversarial Training
• Learning to Generate Reviews and Discovering Sentiment
• Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
• RANet: Ranking Attention Network for Fast Video Object Segmentation
• Auxiliary Deep Generative Models
• Semi-Supervised Sparse Representation Based Classification for Face Recognition with Insufficient Labeled Samples
• Real-world Noisy Image Denoising: A New Benchmark
• External Prior Guided Internal Prior Learning for Real-World Noisy Image Denoising
• Learning View-Specific Deep Networks for Person Re-Identification
• Multi-channel Weighted Nuclear Norm Minimization for Real Color Image Denoising