Domain Agnostic Learning with Disentangled Representations

28 Apr 2019  ·  Xingchao Peng, Zijun Huang, Ximeng Sun, Kate Saenko ·

Unsupervised model transfer has the potential to greatly improve the generalizability of deep models to novel domains. Yet the current literature assumes that the separation of target data into distinct domains is known as a priori. In this paper, we propose the task of Domain-Agnostic Learning (DAL): How to transfer knowledge from a labeled source domain to unlabeled data from arbitrary target domains? To tackle this problem, we devise a novel Deep Adversarial Disentangled Autoencoder (DADA) capable of disentangling domain-specific features from class identity. We demonstrate experimentally that when the target domain labels are unknown, DADA leads to state-of-the-art performance on several image classification datasets.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Multi-target Domain Adaptation DomainNet DADA Accuracy 21.5 # 3

Methods