Adaptive Graph Learning with Semantic Promotability for Domain Adaptation

Domain Adaptation (DA) is used to reduce cross-domain differences between the labeled source and unlabeled target domains. As the existing semantic-based DA approaches mainly focus on extracting consistent knowledge under semantic guidance, they may fail in acquiring (a) personalized knowledge betwe...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence 2024-11, p.1-17
Main Authors: Zheng, Zefeng, Teng, Shaohua, Teng, Luyao, Zhang, Wei, Wu, NaiQi
Format: Article
Language:English
Subjects:
Adaptive Graph Learning
Cows
Domain Adaptation
Ear
Feature extraction
Grasslands
Image segmentation
Implicit Semantics Preservation
Ions
Manifolds
Oceans
Reactive power
Semantically Promotable Sample Enhancement
Semantics
Variant Semantic and Geometrical Component Learning
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Domain Adaptation (DA) is used to reduce cross-domain differences between the labeled source and unlabeled target domains. As the existing semantic-based DA approaches mainly focus on extracting consistent knowledge under semantic guidance, they may fail in acquiring (a) personalized knowledge between intra-class samples, and (b) local knowledge of neighbor samples from different categories. Hence, a multi-semantic-granularity and target-sample oriented approach, called Adaptive Graph Learning with Semantic Promotability (AGLSP), is proposed, which consists of three parts: (a) Adaptive Graph Embedding with Semantic Guidance (AGE-SG) that adaptively estimates the promotability of target samples and learns variant semantic and geometrical components from the source and those semantically promotable target samples; (b) Semantically Promotable Sample Enhancement (SPSE) that further increases the discriminability and adaptability of tag granularity by mining the features of intra-class source and semantically promotable target samples with multi-granularities; and (c) Adaptive Graph Learning with Implicit Semantic Preservation (AGL-ISP) that forms the tag granularity by extracting commonalities between the source and those semantically non-promotable target samples. As AGLSP learns more semantics from the two domains, more cross-domain knowledge is transferred. Mathematical proofs and extensive experiments on seven datasets demonstrate the performance of AGLSP.
ISSN:0162-8828
DOI:10.1109/TPAMI.2024.3507534