论文标题
用gan合成信息丰富的培训样本
Synthesizing Informative Training Samples with GAN
论文作者
论文摘要
通过生成对抗网络（GAN）合成光真实图像，取得了显着的进步。最近，在获取或存储真实的培训数据时，甘斯被用作训练样本发生器甚至是不可行的。但是，传统的gan产生的图像在用于训练深神经网络时的真实训练样本不像真正的培训样本那样丰富。在本文中，我们提出了一种新的方法，可以用GAN（IT-GAN）合成信息性培训样本。具体而言，我们冻结了预训练的GAN模型，并学习与信息性培训样本相对应的信息潜在向量。需要综合图像来保留培训深层神经网络的信息，而不是视觉现实或忠诚度。实验验证了深度神经网络可以更快地学习，并在接受IT-GAN生成的图像训练时获得更好的性能。我们还表明，我们的方法是数据集冷凝问题的有前途解决方案。
Remarkable progress has been achieved in synthesizing photo-realistic images with generative adversarial 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 correspond 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.
