• Home
  • Search
  • Pivot-Guided Embedding for Domain Generalization
  • Cite Icon1
  • https://doi.org/10.1109/access.2022.3225970Copy DOI Icon

Pivot-Guided Embedding for Domain Generalization

Show More
  • Abstract
  • Highlights & Summary
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Neural networks have suffered from a distribution gap between training and test data, known as domain shift. Domain generalization (DG) methods aim to learn domain invariant representations only with limited source domain data to cope with unseen target domains. The main assumption is that the model trained to extract semantically consistent features without any domain specific information is highly adaptable to the unseen target domain. Metric learning allows embedding representations to be class-separated and domain-mixed, which is an optimal condition for DG but has been downplayed in recent works. Even the most popular triplet embedding has limitations in forming an optimal embedding space for DG due to instability. In this paper, we present a novel deep metric learning method for domain invariant representations. Specifically, we propose Pivot-Guided Embedding (PGE), which explicitly forms the entire feature distribution of the embedding space with a novel pivot-guided attraction-repulsion mechanism, to address the instability problem that triplet embedding has. In particular, we leverage pivot features representing a coarse distribution of the entire space as reference points to guide other features toward domain invariant feature distribution. To this end, a pivot selection algorithm is presented to reliably reflect the entire feature distribution. Furthermore, we define Guide-Field, a subspace spanned by a subset of pivots chosen for individual samples, to guide each sample to domain invariant feature space. In a nutshell, the attraction-repulsion mechanism based on pivots, the reliable set of features representing the entire feature distribution, enables the model to extract domain invariant feature representations and also settles the instability problem of triplet loss. Experimental results on three different benchmarks validate the performance advantages of the proposed method over the state-of-the-art DG techniques.

Similar Papers
  • Research Article

Prompt Disentanglement via Language Guidance and Representation Alignment for Domain Generalization.

  • Jun 01, 2026
  • IEEE transactions on pattern analysis and machine intelligence
  • De Cheng +5
  • Conference Article
  • Citations61

Adaptive Mixture of Experts Learning for Generalizable Face Anti-Spoofing

  • Oct 10, 2022
  • Qianyu Zhou +5
  • Research Article
  • Citations49

Knowledge Distillation-Based Domain-Invariant Representation Learning for Domain Generalization

  • Jan 01, 2024
  • IEEE Transactions on Multimedia
  • Ziwei Niu +7
  • Book Chapter
  • Citations3

Learning Cross-Domain Features for Domain Generalization on Point Clouds

  • Jan 01, 2022
  • Hang Xiao +2
  • Research Article

Frequency-aware domain randomization for single-source domain generalization in medical image segmentation.

  • Nov 29, 2025
  • Medical physics
  • Jiayi Wu +6
  • Research Article
  • Citations12

POEM: Polarization of Embeddings for Domain-Invariant Representations

  • Jun 26, 2023
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Sang-Yeong Jo +1
  • Book Chapter
  • Citations10

Bridging the Domain Gap Towards Generalization in Automatic Colorization

  • Jan 01, 2022
  • Hyejin Lee +4
  • Book Chapter

Letting Go of Self-Domain Awareness: Multi-Source Domain-Adversarial Generalization via Dynamic Domain-Weighted Contrastive Transfer Learning

  • Sep 28, 2023
  • Frontiers in artificial intelligence and applications
  • Yuan Ma +5
  • Research Article
  • Citations16

A domain generalization network for imbalanced machinery fault diagnosis

  • Oct 26, 2024
  • Scientific Reports
  • Yu Guo +2
  • Conference Article
  • Citations11

Learning Transferrable and Interpretable Representations for Domain Generalization

  • Oct 17, 2021
  • Zhekai Du +4
  • Research Article
  • Citations19

Domain-invariant feature exploration for intelligent fault diagnosis under unseen and time-varying working conditions

  • Feb 01, 2025
  • Mechanical Systems and Signal Processing
  • Zehui Hua +2
  • Research Article
  • Citations59

Self-Paced Collaborative and Adversarial Network for Unsupervised Domain Adaptation.

  • May 11, 2021
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Weichen Zhang +3
  • Research Article
  • Citations64

CDDSA: Contrastive domain disentanglement and style augmentation for generalizable medical image segmentation.

  • Oct 01, 2023
  • Medical Image Analysis
  • Ran Gu +10
  • Research Article
  • Citations32

Feature concatenation for adversarial domain adaptation

  • Dec 13, 2020
  • Expert Systems with Applications
  • Jingyao Li +2
  • Conference Article
  • Citations115

Single-Domain Generalized Object Detection in Urban Scene via Cyclic-Disentangled Self-Distillation

  • Jun 01, 2022
  • Aming Wu +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.