Attribute-based Regularization of Latent Spaces for Variational Auto-Encoders
| Autor: | Ashis Pati, Alexander Lerch |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
0209 industrial biotechnology Computer Science - Machine Learning business.industry Computer science Auto encoders Monotonic function Pattern recognition Machine Learning (stat.ML) 02 engineering and technology Regularization (mathematics) Machine Learning (cs.LG) 020901 industrial engineering & automation Artificial Intelligence Statistics - Machine Learning 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business Software Generative grammar |
| Popis: | 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 (VAE) 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 that can be used to effectively manipulate a wide range of data attributes spanning image and symbolic music domains. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|