Variational learning across domains with triplet information
arXiv:1806.08672
Abstract
The work investigates deep generative models, which allow us to use training data from one domain to build a model for another domain. We propose the Variational Bi-domain Triplet Autoencoder (VBTA) that learns a joint distribution of objects from different domains. We extend the VBTAs objective function by the relative constraints or triplets that sampled from the shared latent space across domains. In other words, we combine the deep generative models with a metric learning ideas in order to improve the final objective with the triplets information. The performance of the VBTA model is demonstrated on different tasks: image-to-image translation, bi-directional image generation and cross-lingual document classification.
References in corpus (14)
- Adam: A Method for Stochastic Optimization
- Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
- Exploiting Similarities among Languages for Machine Translation
- Deep Convolutional Inverse Graphics Network
- A Survey on Metric Learning for Feature Vectors and Structured Data
- Unsupervised Image-to-Image Translation Networks
- An Autoencoder Approach to Learning Bilingual Word Representations
- DualGAN: Unsupervised Dual Learning for Image-to-Image Translation
- BilBOWA: Fast Bilingual Distributed Representations without Word Alignments
- Joint Multimodal Learning with Deep Generative Models
- Towards Universal Paraphrastic Sentence Embeddings
- Deep Variational Canonical Correlation Analysis
- Bayesian representation learning with oracle constraints
- Generative Models of Visually Grounded Imagination