Timezone: »

 
Synthesizing Informative Training Samples with GAN
Bo Zhao · Hakan Bilen

Fri Dec 02 08:48 AM -- 08:50 AM (PST) @
in Synthetic Data for Empowering ML Research »
Event URL: https://openreview.net/forum?id=frAv0jtUMfS »

Remarkable progress has been achieved in synthesizing photo-realistic images with generative adversarial neural networks (GANs). Recently, GANs are utilized as the training sample generator when obtaining or storing real training data is expensive even infeasible. However, traditional GANs generated images are not as informative as the real training samples when being used to train deep neural networks. In this paper, we propose a novel method to synthesize Informative Training samples with GAN (IT-GAN). Specifically, we freeze a pre-trained GAN model and learn the informative latent vectors that corresponds to informative training samples. The synthesized images are required to preserve information for training deep neural networks rather than visual reality or fidelity. Experiments verify that the deep neural networks can learn faster and achieve better performance when being trained with our IT-GAN generated images. We also show that our method is a promising solution to dataset condensation problem.

Author Information

Bo Zhao (The University of Edinburgh)
Hakan Bilen (University of Edinburgh)

More from the Same Authors