期刊
NEURAL COMPUTING & APPLICATIONS
卷 33, 期 9, 页码 4429-4444出版社
SPRINGER LONDON LTD
DOI: 10.1007/s00521-020-05270-2
关键词
Representation learning; Latent space disentanglement; Latent space regularization; Generative modeling
资金
- Nvidia Corporation
This paper introduces a novel method to structure the latent space of a variational auto-encoder to explicitly encode different continuous-valued attributes. The proposed approach leads to disentangled and interpretable latent spaces, enabling effective manipulation of a wide range of data attributes.
Selective manipulation of data attributes using deep generative models is an active area of research. In this paper, we present a novel method to structure the latent space of a variational auto-encoder to encode different continuous-valued attributes explicitly. This is accomplished by using an attribute regularization loss which enforces a monotonic relationship between the attribute values and the latent code of the dimension along which the attribute is to be encoded. Consequently, post training, the model can be used to manipulate the attribute by simply changing the latent code of the corresponding regularized dimension. The results obtained from several quantitative and qualitative experiments show that the proposed method leads to disentangled and interpretable latent spaces which can be used to effectively manipulate a wide range of data attributes spanning image and symbolic music domains.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据