| 한글제목(Korean Title) |
Bagging deep convolutional autoencoders trained with a mixture of real data and GAN-generated data |
| 영문제목(English Title) |
Bagging deep convolutional autoencoders trained with a mixture of real data and GAN-generated data |
| 저자(Author) |
Cong Hu
Xiao-Jun Wu
Zhen-Qiu Shu
|
| 원문수록처(Citation) |
VOL 13 NO. 11 PP. 5427 ~ 5445 (2019. 11) |
한글내용
(Korean Abstract) |
|
영문내용
(English Abstract) |
While deep neural networks have achieved remarkable performance in representation learning, a huge amount of labeled training data are usually required by supervised deep models such as convolutional neural networks. In this paper, we propose a new representation learning method, namely generative adversarial networks (GAN) based bagging deep convolutional autoencoders (GAN-BDCAE), which can map data to diverse hierarchical representations in an unsupervised fashion. To boost the size of training data, to train deep model and to aggregate diverse learning machines are the three principal avenues towards increasing the capabilities of representation learning of neural networks. We focus on combining those three techniques. To this aim, we adopt GAN for realistic unlabeled sample generation and bagging deep convolutional autoencoders (BDCAE) for robust feature learning. The proposed method improves the discriminative ability of learned feature embedding for solving subsequent pattern recognition problems. We evaluate our approach on three standard benchmarks and demonstrate the superiority of the proposed method compared to traditional unsupervised learning methods.
|
| 키워드(Keyword) |
representation learning
unsupervised learning
generative adversarial networks
deep convolutional autoencoders
bagging
|
| 파일첨부 |
PDF 다운로드
|
