• Home
  • Search
  • Generalized Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Data.
  • Open Access IconOpen Access
  • Cite Icon29
  • https://doi.org/10.1109/tip.2022.3219237Copy DOI Icon

Generalized Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Data.

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

The vanilla Few-shot Learning (FSL) learns to build a classifier for a new concept from one or very few target examples, with the general assumption that source and target classes are sampled from the same domain. Recently, the task of Cross-Domain Few-Shot Learning (CD-FSL) aims at tackling the FSL where there is a huge domain shift between the source and target datasets. Extensive efforts on CD-FSL have been made via either directly extending the meta-learning paradigm of vanilla FSL methods, or employing massive unlabeled target data to help learn models. In this paper, we notice that in the CD-FSL task, the few labeled target images have never been explicitly leveraged to inform the model in the training stage. However, such a labeled target example set is very important to bridge the huge domain gap. Critically, this paper advocates a more practical training scenario for CD-FSL. And our key insight is to utilize a few labeled target data to guide the learning of the CD-FSL model. Technically, we propose a novel Generalized Meta-learning based Feature-Disentangled Mixup network, namely GMeta-FDMixup. We make three key contributions of utilizing GMeta-FDMixup to address CD-FSL. Firstly, we present two mixup modules - mixup-P and mixup-M that help facilitate utilizing the unbalanced and disjoint source and target datasets. These two novel modules enable diverse image generation for training the model on the source domain. Secondly, to narrow the domain gap explicitly, we contribute a novel feature disentanglement module that learns to decouple the domain-irrelevant and domain-specific features. By stripping the domain-specific features, we alleviate the negative effects caused by the domain inductive bias. Finally, we repurpose a new contrastive learning module, dubbed ConL. ConL prevents the model from only capturing category-related features via introducing contrastive loss. Thus, the generalization ability on novel categories is improved. Extensive experimental results on two benchmarks show the superiority of our setting and the effectiveness of our method. Code and models will be released.

Similar Papers
  • Research Article
  • Citations1

A deep cross-domain tree species classification framework via local maximum mean discrepancy and few-shot learning

  • Jan 01, 2025
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Long Chen +5
  • Conference Article
  • Citations86

Meta-FDMixup

  • Oct 17, 2021
  • Yuqian Fu +2
  • Conference Article
  • Citations1

Target Guided Knowledge Distillation for Cross-Domain Few-Shot Learning

  • Nov 03, 2023
  • Xinyi Chang +2
  • Conference Article
  • Citations61

Ranking Distance Calibration for Cross-Domain Few-Shot Learning

  • Jun 01, 2022
  • Pan Li +3
  • Conference Article
  • Citations77

Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencoder

  • Oct 01, 2021
  • Hanwen Liang +3
  • Conference Article
  • Citations3

SLA+: Narrowing the Difference between Data Sets in Heterogenous Cross-Project Defection Prediction

  • Jul 01, 2020
  • Jie Wu +3
  • PDF
  • Research Article
  • Citations2

Target Oriented Dynamic Adaption for Cross-Domain Few-Shot Learning

  • Apr 27, 2024
  • Neural Processing Letters
  • Xinyi Chang +4
  • Research Article
  • Citations14

Who is closer: A computational method for domain gap evaluation

  • Sep 01, 2021
  • Pattern Recognition
  • Xiaobin Liu +1
  • Research Article
  • Citations27

Multilevel Noise Contrastive Network for Few-Shot Image Denoising

  • Jan 01, 2022
  • IEEE Transactions on Instrumentation and Measurement
  • Bo Jiang +4
  • Research Article
  • Citations11

Spectral Decomposition and Transformation for Cross-domain Few-shot Learning

  • Jul 14, 2024
  • Neural Networks
  • Yicong Liu +3
  • Conference Article
  • Citations23

ME-D2N: Multi-Expert Domain Decompositional Network for Cross-Domain Few-Shot Learning

  • Oct 10, 2022
  • Yuqian Fu +4
  • Research Article
  • Citations1

Adaptive Transfer Learning for Time-to-Event Modeling with Applications in Disease Risk Assessment.

  • May 12, 2025
  • medRxiv : the preprint server for health sciences
  • Yuying Lu +2
  • Research Article
  • Citations1

Adaptive transfer learning for time-to-event modeling with applications in disease risk assessment.

  • Jan 20, 2026
  • Biostatistics (Oxford, England)
  • Yuying Lu +2
  • Research Article
  • Citations9

Learning general features to bridge the cross-domain gaps in few-shot learning

  • Jun 08, 2024
  • Knowledge-Based Systems
  • Xiang Li +8
  • Research Article
  • Citations26

A topic sentence-based instance transfer method for imbalanced sentiment classification of Chinese product reviews

  • Oct 30, 2015
  • Electronic Commerce Research and Applications
  • Feng Tian +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.