• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

¿µ¹® ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ¿µ¹® ³í¹®Áö > TIIS (Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ)

TIIS (Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ)

Current Result Document : 7 / 7 ÀÌÀü°Ç ÀÌÀü°Ç

ÇѱÛÁ¦¸ñ(Korean Title) Bagging deep convolutional autoencoders trained with a mixture of real data and GAN-generated data
¿µ¹®Á¦¸ñ(English Title) Bagging deep convolutional autoencoders trained with a mixture of real data and GAN-generated data
ÀúÀÚ(Author) Cong Hu   Xiao-Jun Wu   Zhen-Qiu Shu  
¿ø¹®¼ö·Ïó(Citation) VOL 13 NO. 11 PP. 5427 ~ 5445 (2019. 11)
Çѱ۳»¿ë
(Korean Abstract)
¿µ¹®³»¿ë
(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.
Å°¿öµå(Keyword) representation learning   unsupervised learning   generative adversarial networks   deep convolutional autoencoders   bagging  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå