Progressive Domain Expansion Network for Single Domain Generalization

03/30/2021
by   Lei Li, et al.
0

Single domain generalization is a challenging case of model generalization, where the models are trained on a single domain and tested on other unseen domains. A promising solution is to learn cross-domain invariant representations by expanding the coverage of the training domain. These methods have limited generalization performance gains in practical applications due to the lack of appropriate safety and effectiveness constraints. In this paper, we propose a novel learning framework called progressive domain expansion network (PDEN) for single domain generalization. The domain expansion subnetwork and representation learning subnetwork in PDEN mutually benefit from each other by joint learning. For the domain expansion subnetwork, multiple domains are progressively generated in order to simulate various photometric and geometric transforms in unseen domains. A series of strategies are introduced to guarantee the safety and effectiveness of the expanded domains. For the domain invariant representation learning subnetwork, contrastive learning is introduced to learn the domain invariant representation in which each class is well clustered so that a better decision boundary can be learned to improve it's generalization. Extensive experiments on classification and segmentation have shown that PDEN can achieve up to 15.28 state-of-the-art single-domain generalization methods.

READ FULL TEXT

page 1

page 3

page 4

research
02/09/2021

Domain Invariant Representation Learning with Domain Density Transformations

Domain generalization refers to the problem where we aim to train a mode...
research
02/25/2021

Model-Based Domain Generalization

We consider the problem of domain generalization, in which a predictor i...
research
05/25/2023

Quantitatively Measuring and Contrastively Exploring Heterogeneity for Domain Generalization

Domain generalization (DG) is a prevalent problem in real-world applicat...
research
09/18/2019

Towards Shape Biased Unsupervised Representation Learning for Domain Generalization

It is known that, without awareness of the process, our brain appears to...
research
12/21/2022

Target Conditioned Representation Independence (TCRI); From Domain-Invariant to Domain-General Representations

We propose a Target Conditioned Representation Independence (TCRI) objec...
research
07/25/2022

Domain-invariant Feature Exploration for Domain Generalization

Deep learning has achieved great success in the past few years. However,...
research
02/20/2021

On Calibration and Out-of-domain Generalization

Out-of-domain (OOD) generalization is a significant challenge for machin...

Please sign up or login with your details

Forgot password? Click here to reset