• Home
  • Search
  • Deep transferable label propagation with prototypical augmentation.
  • https://doi.org/10.1038/s41598-026-53642-wCopy DOI Icon

Deep transferable label propagation with prototypical augmentation.

Show More
  • Abstract
  • Literature Map
  • Similar Papers
Abstract

Domain adaptation (DA) seeks to utilize ample labeled data from a source domain to boost the generalization capability of models on an unlabeled target domain with divergent data distributions. Label Propagation (LP) has emerged as an efficient semi-supervised learning paradigm for DA, transferring labels between the source and target domains based on a similarity graph. Nevertheless, existing LP-based DA methods still face significant challenges: (1) Semantic insufficiency in the source training domain impairs the performance of classes with sparse structures, particularly minority classes; (2) Generated pseudo-labels exhibit low reliability due to ambiguous feature distributions; (3) The two-phase architecture decouples domain-invariant feature learning from label propagation, thus failing to achieve mutual enhancement between these two processes for DA tasks; (4) Sample-level graph construction incurs prohibitive computational costs and poor scalability when handling large-scale datasets. To address these issues, we propose a novel DA strategy, Deep Transferable Label Propagation (DTLP), that integrates prototypical augmentation techniques. Specifically, DTLP embeds three core modules into a unified end-to-end system: (1) Prototype-guided feature augmentation, termed Prototypical Augmentation (ProAug), which enriches the semantic content of the source domain by interpolating samples with class prototypes to mitigate semantic deficiency; (2) Prototype graph-based label propagation, which constructs a class-level prototypical graph rather than a sample-level one to reduce computational complexity and alleviate class imbalance; (3) Domain alignment via prototypical contrastive learning, which facilitates dynamic mutual optimization between domain-invariant feature extraction and robust label propagation while narrowing domain discrepancy. Comprehensive experiments on various benchmark datasets demonstrate that the proposed DTLP outperforms state-of-the-art LP-based DA methods, validating its effectiveness and generalizability.

Similar Papers
  • Research Article
  • Citations2

Foreground object structure transfer for unsupervised domain adaptation

  • Aug 08, 2022
  • International Journal of Intelligent Systems
  • Jieren Cheng +5
  • PDF
  • Research Article
  • Citations40

Multitarget Domain Adaptation for Remote Sensing Classification Using Graph Neural Network

  • Jan 01, 2022
  • IEEE Geoscience and Remote Sensing Letters
  • Sudipan Saha +2
  • Research Article
  • Citations45

Universal multi-Source domain adaptation for image classification

  • Aug 14, 2021
  • Pattern Recognition
  • Yueming Yin +3
  • Research Article
  • Citations32

Feature concatenation for adversarial domain adaptation

  • Dec 13, 2020
  • Expert Systems with Applications
  • Jingyao Li +2
  • Research Article
  • Citations37

Unsupervised Adversarial Domain Adaptation Network for Semantic Segmentation

  • Dec 26, 2019
  • IEEE Geoscience and Remote Sensing Letters
  • Wei Liu +1
  • Research Article
  • Citations15

Sparsely-labeled source assisted domain adaptation

  • Jan 08, 2021
  • Pattern Recognition
  • Wei Wang +8
  • Conference Article

Joint Distribution Adaptation via Wasserstein Adversarial Training

  • Jul 18, 2021
  • Xiaolu Wang +3
  • Research Article

Open-Set Heterogeneous Domain Adaptation: Theoretical Analysis and Algorithm.

  • Apr 11, 2025
  • Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence
  • Thai-Hoang Pham +4
  • Research Article
  • Citations30

Source data-free domain adaptation for a faster R-CNN

  • Nov 19, 2021
  • Pattern Recognition
  • Lin Xiong +4
  • Conference Article
  • Citations3

Domain Adaptation and Super-Resolution Based Bi-Directional Semantic Segmentation Method for Remote Sensing Images

  • Jul 17, 2022
  • Min Liang +1
  • Research Article
  • Citations13

Robust Hyperspectral Image Domain Adaptation With Noisy Labels

  • Jul 01, 2019
  • IEEE Geoscience and Remote Sensing Letters
  • Wei Wei +5
  • Research Article

DW-D3A: dynamic weighted dual-driven domain adaptation for cross-scene hyperspectral image classification

  • Jul 01, 2024
  • International Journal of Remote Sensing
  • Ao Li +4
  • Research Article
  • Citations11

GLGAT-CFSL: Global-Local Graph Attention Network-Based Cross-Domain Few-Shot Learning for Hyperspectral Image Classification

  • Jan 01, 2024
  • IEEE Transactions on Geoscience and Remote Sensing
  • Chen Ding +7
  • Research Article
  • Citations40

Source-Free Multidomain Adaptation With Fuzzy Rule-Based Deep Neural Networks

  • Dec 01, 2023
  • IEEE Transactions on Fuzzy Systems
  • Keqiuyin Li +3
  • Research Article
  • Citations24

Semi-supervised domain adaptation for segmentation models on different monitoring settings

  • May 01, 2023
  • Automation in Construction
  • Yeji Hong +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.