Semantically Decomposing the Latent Spaces of Generative Adversarial Networks
Semantically Decomposing the Latent Spaces of Generative Adversarial Networks
复制标题
DOI：
--
复制
发表时间：
2017-05
期刊：
影响因子：
--
通讯作者：
Chris Donahue;Zachary Chase Lipton;Akshay Balsubramani;Julian McAuley
中科院分区：
文献类型：
--
作者：
Chris Donahue;Zachary Chase Lipton;Akshay Balsubramani;Julian McAuley
我们提出了一种用于训练生成对抗网络的新算法，该算法联合学习身份（例如个人）和观察（例如特定照片）的潜在代码。通过固定潜在代码的身份部分，我们可以生成同一主题的不同图像，通过固定观察部分，我们可以遍历主题的流形，同时保持偶然的方面，如照明和姿势。我们的算法具有成对的训练方案，其中来自生成器的每个样本由具有共同身份码的两个图像组成。来自真实的数据集的相应样本由同一主题的两张不同照片组成。为了欺骗机器人，生成器必须产生照片般逼真的、不同的、看起来描绘同一个人的配对。我们用Siamese鉴别器增强DCGAN和BEGAN方法，以促进成对训练。人类法官和现成的人脸验证系统的实验表明，我们的算法的能力，以产生令人信服的，身份匹配的照片。
We propose a new algorithm for training generative adversarial networks that jointly learns latent codes for both identities (e.g. individual humans) and observations (e.g. specific photographs). By fixing the identity portion of the latent codes, we can generate diverse images of the same subject, and by fixing the observation portion, we can traverse the manifold of subjects while maintaining contingent aspects such as lighting and pose. Our algorithm features a pairwise training scheme in which each sample from the generator consists of two images with a common identity code. Corresponding samples from the real dataset consist of two distinct photographs of the same subject. In order to fool the discriminator, the generator must produce pairs that are photorealistic, distinct, and appear to depict the same individual. We augment both the DCGAN and BEGAN approaches with Siamese discriminators to facilitate pairwise training. Experiments with human judges and an off-the-shelf face verification system demonstrate our algorithm's ability to generate convincing, identity-matched photographs.