Inter-Class and Inter-Domain Semantic Augmentation for Domain Generalization

Mengzhu Wang

doi:10.1109/TIP.2024.3354420

Inter-Class and Inter-Domain Semantic Augmentation for Domain Generalization

2024-01-01

9

PRE

AI

DOI：10.1109/TIP.2024.3354420

Original

Original request for help

Save

Abstract

En 中文

The domain generalization approach seeks to develop a universal model that performs well on unknown target domains with the aid of diverse source domains. Data augmentation has proven to be an effective method to enhance domain generalization in computer vision. Recently, semantic-level based data augmentation has yielded remarkable results. However, these methods focus on sampling semantic directions on feature space from intra-class and intra-domain, limiting the diversity of the source domain. To address this issue, we propose a novel approach called Inter-Class and Inter-Domain Semantic Augmentation (CDSA) for domain generalization. We first introduce a sampling-based method called CrossSmooth to obtain semantic directions from inter-class. Then, CrossVariance obtains the styles of different domains by sampling semantic directions. Our experiments on four well-known domain generalization benchmark datasets (Digits-DG, PACS, Office-Home, and DomainNet) demonstrate the effectiveness of our approach. We also validate our approach on commonly-used semantic segmentation datasets, namely GTAV, SYNTHIA, Cityscapes, Mapillary, and BDDS which also show significant improvements.

Keywords:

Semantics

Data augmentation

Training

Self-supervised learning

Painting

Data models

Picture archiving and communication systems

Domain generalization

data augmentation

inter-class

inter-domain

Inter-Class and Inter-Domain Semantic Augmentation for Domain Generalization

Abstract

Journal

Organization