D UAL SPACE LEARNING WITH VARIATIONAL AUTOEN-CODERS
D UAL SPACE LEARNING WITH VARIATIONAL AUTOEN-CODERS
复制标题
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Hirono Okamoto;I. Higuchi
中科院分区：
文献类型：
--
作者：
Hirono Okamoto;I. Higuchi
本文提出了一种双变分自动编码器（DualVAE），用于生成对应于多类标签的图像的框架。最近对条件生成模型的研究，如条件VAE，通过改变标签来展示图像传输。然而，当多类标签的维度很大时，这些模型无法改变与标签对应的图像，因为需要学习相应类的多个分布才能传输图像。这导致缺乏训练数据。因此，我们不是用标签来调节，而是用包含标签信息的潜在向量来调节。DualVAE使用标签通过线性决策边界划分潜在空间的一个分布。因此，DualVAE可以很容易地通过向决策边界移动潜在向量来传输图像，并且对多类标签的缺失值具有鲁棒性。为了评估我们所提出的方法，我们引入了一个条件初始分数（CIS）来衡量图像对目标类的变化。我们使用CelebA数据集中的CIS评估了DualVAE传输的图像，并在多类设置中展示了最先进的性能。
This paper proposes a dual variational autoencoder (DualVAE), a framework for generating images corresponding to multiclass labels. Recent research on conditional generative models, such as the Conditional VAE, exhibit image transfer by changing labels. However, when the dimension of multiclass labels is large, these models cannot change images corresponding to labels, because learning multiple distributions of the corresponding class is necessary to transfer an image. This leads to the lack of training data. Therefore, instead of conditioning with labels, we condition with latent vectors that include label information. DualVAE divides one distribution of the latent space by linear decision boundaries using labels. Consequently, DualVAE can easily transfer an image by moving a latent vector toward a decision boundary and is robust to the missing values of multiclass labels. To evaluate our proposed method, we introduce a conditional inception score (CIS) for measuring how much an image changes to the target class. We evaluate the images transferred by DualVAE using the CIS in CelebA datasets and demonstrate state-of-the-art performance in a multiclass setting.