Multiple Domain Generalization Using Category Information Independent of Domain Differences

TL;DR

This paper introduces a novel segmentation method that isolates category information from domain differences and uses SQ-VAE to adapt to unseen domains, improving accuracy in vascular and cell nucleus segmentation.

Contribution

The authors propose a new approach that separates domain-independent category information and employs SQ-VAE to handle domain gaps, enhancing segmentation performance across diverse datasets.

Findings

Improved segmentation accuracy over conventional methods.

Effective separation of category information from domain differences.

Successful application to vascular and cell nucleus segmentation datasets.

Abstract

Domain generalization is a technique aimed at enabling models to maintain high accuracy when applied to new environments or datasets (unseen domains) that differ from the datasets used in training. Generally, the accuracy of models trained on a specific dataset (source domain) often decreases significantly when evaluated on different datasets (target domain). This issue arises due to differences in domains caused by varying environmental conditions such as imaging equipment and staining methods. Therefore, we undertook two initiatives to perform segmentation that does not depend on domain differences. We propose a method that separates category information independent of domain differences from the information specific to the source domain. By using information independent of domain differences, our method enables learning the segmentation targets (e.g., blood vessels and cell nuclei). Although we extract independent information of domain differences, this cannot completely bridge the domain gap between training and test data. Therefore, we absorb the domain gap using the quantum vectors in Stochastically Quantized Variational AutoEncoder (SQ-VAE). In experiments, we evaluated our method on datasets for vascular segmentation and cell nucleus segmentation. Our methods improved the accuracy compared to conventional methods.