Domain Invariant Representation Learning with Domain Density Transformations
arXiv:2102.05082
Abstract
Domain generalization refers to the problem where we aim to train a model on data from a set of source domains so that the model can generalize to unseen target domains. Naively training a model on the aggregate set of data (pooled from all source domains) has been shown to perform suboptimally, since the information learned by that model might be domain-specific and generalize imperfectly to target domains. To tackle this problem, a predominant approach is to find and learn some domain-invariant information in order to use it for the prediction task. In this paper, we propose a theoretically grounded method to learn a domain-invariant representation by enforcing the representation network to be invariant under all transformation functions among domains. We also show how to use generative adversarial networks to learn such domain transformations to implement our method in practice. We demonstrate the effectiveness of our method on several widely used datasets for the domain generalization problem, on all of which we achieve competitive results with state-of-the-art models.
NeurIPS 2021
References in corpus (8)
- Domain Generalization via Invariant Feature Representation
- Big Self-Supervised Models are Strong Semi-Supervised Learners
- Bridging Theory and Algorithm for Domain Adaptation
- On Learning Invariant Representation for Domain Adaptation
- Learning Robust Representations by Projecting Superficial Statistics Out
- Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift
- Efficient Domain Generalization via Common-Specific Low-Rank Decomposition
- Respecting Domain Relations: Hypothesis Invariance for Domain Generalization