Matching Embeddings for Domain Adaptation
arXiv:1909.11651
Abstract
In this work we address the problem of transferring knowledge obtained from a vast annotated source domain to a low labeled target domain. We propose Adversarial Variational Domain Adaptation (AVDA), a semi-supervised domain adaptation method based on deep variational embedded representations. We use approximate inference and domain adversarial methods to map samples from source and target domains into an aligned class-dependent embedding defined as a Gaussian Mixture Model. AVDA works as a classifier and considers a generative model that helps this classification. We used digits dataset for experimentation. Our results show that on a semi-supervised few-shot scenario our model outperforms previous methods in most of the adaptation tasks, even using a fewer number of labeled samples per class on target domain.
arXiv comment12 pages, 3 figures
References in corpus (18)
- Auto-Encoding Variational Bayes
- How transferable are features in deep neural networks?
- Categorical Reparameterization with Gumbel-Softmax
- Learning Transferable Features with Deep Adaptation Networks
- Deep Domain Confusion: Maximizing for Domain Invariance
- Deep Visual Domain Adaptation: A Survey
- CANDELS: The Cosmic Assembly Near-infrared Deep Extragalactic Legacy Survey
- The Great Observatories Origins Deep Survey: Initial Results From Optical and Near-Infrared Imaging
- Conditional Adversarial Domain Adaptation
- Cluster Lensing And Supernova survey with Hubble (CLASH): An Overview
- Semi-Supervised Learning with Ladder Networks
- Semi-Supervised Learning with Generative Adversarial Networks
- A DIRT-T Approach to Unsupervised Domain Adaptation
- Auxiliary Deep Generative Models
- Bridging Theory and Algorithm for Domain Adaptation
- Augmented Cyclic Adversarial Learning for Low Resource Domain Adaptation
- Learning Loss Functions for Semi-supervised Learning via Discriminative Adversarial Networks
- Deep Variational Transfer: Transfer Learning through Semi-supervised Deep Generative Models