Domain Agnostic Learning with Disentangled Representations
Xingchao Peng · Zijun Huang · Ximeng Sun · Kate Saenko

Wed Jun 12th 02:00 -- 02:20 PM @ Room 201

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 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.

Author Information

Xingchao Peng (Boston University)
Zijun Huang (Columbia University)
Ximeng Sun (Boston University)
Kate Saenko (Boston University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors