mlsanityData to 14 Oct 2026

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

arXiv 2107.11978 ↗First posted 26 Jul 2021cs.CVcited by 48

Not on the map. Why?

Abstract (arXiv)

A recent study finds that existing few-shot learning methods, trained on the source domain, fail to generalize to the novel target domain when a domain gap is observed. This motivates the task of Cross-Domain Few-Shot Learning (CD-FSL). In this paper, we realize that the labeled target data in CD-FSL has not been leveraged in any way to help the learning process. Thus, we advocate utilizing few labeled target data to guide the model learning. Technically, a novel meta-FDMixup network is proposed. We tackle this problem mainly from two aspects. Firstly, to utilize the source and the newly introduced target data of two different class sets, a mixup module is re-proposed and integrated into the meta-learning mechanism. Secondly, a novel disentangle module together with a domain classifier is proposed to extract the disentangled domain-irrelevant and domain-specific features. These two modules together enable our model to narrow the domain gap thus generalizing well to the target datasets. Additionally, a detailed feasibility and pilot study is conducted to reflect the intuitive understanding of CD-FSL under our new setting. Experimental results show the effectiveness of our new setting and the proposed method. Codes and models are available at https://github.com/lovelyqian/Meta-FDMixup.

Key facts. Cited by 48 papers in the map (data through 14 Oct 2026). Builds on 41 of its 58 references that are in the map. First posted on arXiv 26 Jul 2021.

Builds on

41 of 58 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  6. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  7. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  8. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  9. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  10. 2016Matching Networks for One Shot Learningcited by 2,255
  11. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,496
  12. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
29 more
  1. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 972
  2. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 901
  3. 2019A Closer Look at Few-shot Classificationcited by 684
  4. 2019Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)cited by 669
  5. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 600
  6. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  7. 2019Contrastive Adaptation Network for Unsupervised Domain Adaptationcited by 407
  8. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  9. 2016Domain Separation Networkscited by 320
  10. 2016Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networkscited by 308
  11. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 294
  12. 2020Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixupcited by 261
  13. 2016Using Deep Learning for Image-Based Plant Disease Detectioncited by 219
  14. 2019Cross Attention Network for Few-shot Classificationcited by 219
  15. 2015Simultaneous Deep Transfer Across Domains and Taskscited by 206
  16. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 185
  17. 2016Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptationcited by 163
  18. 2020Adversarial Feature Hallucination Networks for Few-Shot Learningcited by 110
  19. 2016Beyond Sharing Weights for Deep Domain Adaptationcited by 80
  20. 2020Self-training for Few-shot Transfer Across Extreme Task Differencescited by 76
  21. 2021Cross-Domain Few-Shot Classification via Adversarial Task Augmentationcited by 63
  22. 2020Explanation-Guided Training for Cross-Domain Few-Shot Classificationcited by 58
  23. 2020Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognitioncited by 50
  24. 2020Cross-Domain Few-Shot Learning by Representation Fusioncited by 32
  25. 2020Feature Transformation Ensemble Model with Batch Spectral Regularization for Cross-Domain Few-Shot Classificationcited by 20
  26. 2020Large Margin Mechanism and Pseudo Query Set on Cross-Domain Few-Shot Learningcited by 8
  27. 2020Optimization of Image Embeddings for Few Shot Learningcited by 6
  28. 2020XMixup: Efficient Transfer Learning with Auxiliary Samples by Cross-domain Mixupcited by 5
  29. 2020SB-MTL: Score-based Meta Transfer-Learning for Cross-Domain Few-Shot Learningcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 8; 2023: 12; 2024: 14; 2025: 9; 2026: 4.

48 papers.

Sort:

By area:

  1. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 163
  2. 2023DePT: Decoupled Prompt Tuningcited by 58
  3. 2023StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learningcited by 53
  4. 2024Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detectorcited by 43
  5. 2022Multiple-environment Self-adaptive Network for Aerial-view Geo-localizationcited by 37
  6. 2022Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignmentcited by 29
  7. 2021Ranking Distance Calibration for Cross-Domain Few-Shot Learningcited by 27
  8. 2022Wave-SAN: Wavelet based Style Augmentation Network for Cross-Domain Few-Shot Learningcited by 23
  9. 2025EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answeringcited by 21
  10. 2025EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmarkcited by 19
  11. 2023From Global to Local: Multi-scale Out-of-distribution Detectioncited by 18
  12. 2025Reliable Few-shot Learning under Dual Noisescited by 17
36 more
  1. 2022TGDM: Target Guided Dynamic Mixup for Cross-Domain Few-Shot Learningcited by 16
  2. 2025Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detectioncited by 15
  3. 2023Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Surveycited by 14
  4. 2023DETA: Denoised Task Adaptation for Few-Shot Learningcited by 13
  5. 2024Enhancing Information Maximization with Distance-Aware Contrastive Learning for Source-Free Cross-Domain Few-Shot Learningcited by 13
  6. 2023On the Importance of Spatial Relations for Few-shot Action Recognitioncited by 11
  7. 2024Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learningcited by 11
  8. 2023From Channel Bias to Feature Redundancy: Uncovering the "Less is More" Principle in Few-Shot Learningcited by 10
  9. 2024Prompt as Free Lunch: Enhancing Diversity in Source-Free Cross-domain Few-shot Learning through Semantic-Guided Promptingcited by 10
  10. 2024Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselvescited by 10
  11. 2022ME-D2N: Multi-Expert Domain Decompositional Network for Cross-Domain Few-Shot Learningcited by 9
  12. 2024Exploring Cross-Domain Few-Shot Classification via Frequency-Aware Promptingcited by 9
  13. 2025A Closer Look at Conditional Prompt Tuning for Vision-Language Modelscited by 8
  14. 2022Cross-Domain Cross-Set Few-Shot Learning via Learning Compact and Aligned Representationscited by 5
  15. 2024Towards Few-Shot Learning in the Open World: A Review and Beyondcited by 5
  16. 2024Step-wise Distribution Alignment Guided Style Prompt Tuning for Source-free Cross-domain Few-shot Learningcited by 5
  17. 2022Cross-Domain Few-Shot Classification via Inter-Source Stylizationcited by 4
  18. 2023Domain Adaptive Few-Shot Open-Set Learningcited by 4
  19. 2024Few-Shot Image Quality Assessment via Adaptation of Vision-Language Modelscited by 4
  20. 2024TAVP: Task-Adaptive Visual Prompt for Cross-domain Few-shot Segmentationcited by 4
  21. 2025Random Registers for Cross-Domain Few-Shot Learningcited by 4
  22. 2023A Survey of Deep Visual Cross-Domain Few-Shot Learningcited by 3
  23. 2023Cross-Level Distillation and Feature Denoising for Cross-Domain Few-Shot Classificationcited by 3
  24. 2025Revisiting Continuity of Image Tokens for Cross-domain Few-shot Learningcited by 3
  25. 2024Understanding the Cross-Domain Capabilities of Video-Based Few-Shot Action Recognition Modelscited by 2
  26. 2026Addressing Exacerbated Attention Sink for Source-Free Cross-Domain Few-Shot Learningcited by 2
  27. 2023Exploiting Style Transfer-based Task Augmentation for Cross-Domain Few-Shot Learningcited by 1
  28. 2023Generalized Cross-domain Multi-label Few-shot Learning for Chest X-rayscited by 1
  29. 2026Prompt-Driven Simulation with Feature Perturbation for Cross-Domain Few-Shot Object Detectioncited by 1
  30. 2024Feature Aligning Few shot Learning Method Using Local Descriptors Weighted Rulescited by 0
  31. 2024Local Descriptors Weighted Adaptive Threshold Filtering For Few-Shot Learningcited by 0
  32. 2024Embedding Space Allocation with Angle-Norm Joint Classifiers for Few-Shot Class-Incremental Learningcited by 0
  33. 2025Few-shot Classification as Multi-instance Verification: Effective Backbone-agnostic Transfer across Domainscited by 0
  34. 2025FreqGRL: Suppressing Low-Frequency Bias and Mining High-Frequency Knowledge for Cross-Domain Few-Shot Learningcited by 0
  35. 2026The First EgoCross Challenge at EgoVis 2026: Cross-Domain Egocentric Video Question Answeringcited by 0
  36. 2026Are We Really Doing Few-Shot Learning? A Critical Examination of Pre-Training Assumptionscited by 0