.png){kind=icon}
.png){kind=icon}
Return
Continuous Disentangled Joint Space Learning for Domain Generalization
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2024.3454689.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Domain generalization (DG) aims to learn a model on one or multiple observed source domains that can generalize to unseen target test domains. Previous approaches have focused on extracting domain-invariant information from multiple source domains, but domain-specific information is also closely tied to semantics in individual domains and is not well-suited for generalization to the target domain. In this article, we propose a novel DG method called continuous disentangled joint space learning (CJSL), which leverages both domain-invariant and domain-specific information for more effective DG. The key idea behind CJSL is to formulate and learn a continuous joint space (CJS) for domain-specific representations from source domains through iterative feature disentanglement. This learned CJS can then be used to simulate domain-specific representations for test samples from a mixture of multiple domains via Monte Carlo sampling during the inference stage. Unlike existing approaches, which exploit domain-invariant feature vectors only or aim to learn a universal domain-specific feature extractor, we simulate domain-specific representations via sampling the latent vectors in the learned CJS for the test sample to fully use the power of multiple domain-specific classifiers for robust prediction. Empirical results demonstrate that CJSL outperforms 19 state-of-the-art (SOTA) methods on seven benchmarks, indicating the effectiveness of our proposed method.
Keywords:
Feature extraction
Vectors
Data models
Training
Semantics
Monte Carlo methods
Metalearning
Domain generalization (DG)
feature disentanglement
robust machine learning
Journal
IF:
8.9
Papers:
7.5K
Citations:
7.2W