.png){kind=icon}
.png){kind=icon}
Return
Batch normalization emb e ddings for deep domain generalization
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2022.109115.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Domain generalization aims at training machine learning models to perform robustly across different and unseen domains. Several methods train models from multiple datasets to extract domain-invariant features, hoping to generalize to unseen domains. Instead, first we explicitly train domain-dependent representations leveraging ad-hoc batch normalization layers to collect independent domain's statistics. Then, we propose to use these statistics to map domains in a shared latent space, where membership to a domain is measured by means of a distance function. At test time, we project samples from an unknown domain into the same space and infer properties of their domain as a linear combination of the known ones. We apply the same mapping strategy at training and test time, learning both a latent representation and a powerful but lightweight ensemble model. We show a significant increase in classification accuracy over current state-of-the-art techniques on popular domain generalization benchmarks: PACS, Office-31 and Office-Caltech.(c) 2022 Elsevier Ltd. All rights reserved.
Keywords:
Domain generalization
Domain representation learning
Learning from multiple sources
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.