Variational Disentanglement for Domain Generalization

by   Yufei Wang, et al.
City University of Hong Kong
Nanyang Technological University

Domain generalization aims to learn an invariant model that can generalize well to the unseen target domain. In this paper, we propose to tackle the problem of domain generalization by delivering an effective framework named Variational Disentanglement Network (VDN), which is capable of disentangling the domain-specific features and task-specific features, where the task-specific features are expected to be better generalized to unseen but related test data. We further show the rationale of our proposed method by proving that our proposed framework is equivalent to minimize the evidence upper bound of the divergence between the distribution of task-specific features and its invariant ground truth derived from variational inference. We conduct extensive experiments to verify our method on three benchmarks, and both quantitative and qualitative results illustrate the effectiveness of our method.


page 3

page 6

page 7


Domain Invariant Representation Learning with Domain Density Transformations

Domain generalization refers to the problem where we aim to train a mode...

Disentanglement by Cyclic Reconstruction

Deep neural networks have demonstrated their ability to automatically ex...

Adaptive Mixture of Experts Learning for Generalizable Face Anti-Spoofing

With various face presentation attacks emerging continually, face anti-s...

Invariant Information Bottleneck for Domain Generalization

The main challenge for domain generalization (DG) is to overcome the pot...

Hierarchical Domain Invariant Variational Auto-Encoding with weak domain supervision

We address the task of domain generalization, where the goal is to train...

Constrained Maximum Cross-Domain Likelihood for Domain Generalization

As a recent noticeable topic, domain generalization aims to learn a gene...

Please sign up or login with your details

Forgot password? Click here to reset