DeepAI AI Chat
Log In Sign Up

Domain Agnostic Learning with Disentangled Representations

by   Xingchao Peng, et al.

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.


Domain-Agnostic Learning with Anatomy-Consistent Embedding for Cross-Modality Liver Segmentation

Domain Adaptation (DA) has the potential to greatly help the generalizat...

Cyclically Disentangled Feature Translation for Face Anti-spoofing

Current domain adaptation methods for face anti-spoofing leverage labele...

Disentangled State Space Representations

Sequential data often originates from diverse domains across which stati...

Representation Learning Through Latent Canonicalizations

We seek to learn a representation on a large annotated data source that ...

Learning task-agnostic representation via toddler-inspired learning

One of the inherent limitations of current AI systems, stemming from the...

Robust Domain-Free Domain Generalization with Class-aware Alignment

While deep neural networks demonstrate state-of-the-art performance on a...