mlsanityData to 14 Oct 2026

Ranking Distance Calibration for Cross-Domain Few-Shot Learning

arXiv 2112.00260 ↗First posted 1 Dec 2021cs.CV cs.LGcited by 27

Not on the map. Why?

Abstract (arXiv)

Recent progress in few-shot learning promotes a more realistic cross-domain setting, where the source and target datasets are from different domains. Due to the domain gap and disjoint label spaces between source and target datasets, their shared knowledge is extremely limited. This encourages us to explore more information in the target domain rather than to overly elaborate training strategies on the source domain as in many existing methods. Hence, we start from a generic representation pre-trained by a cross-entropy loss and a conventional distance-based classifier, along with an image retrieval view, to employ a re-ranking process for calibrating a target distance matrix by discovering the reciprocal k-nearest neighbours within the task. Assuming the pre-trained representation is biased towards the source, we construct a non-linear subspace to minimise task-irrelevant features therewithin while keep more transferrable discriminative information by a hyperbolic tangent transformation. The calibrated distance in this target-aware non-linear subspace is complementary to that in the pre-trained representation. To impose such distance calibration information onto the pre-trained representation, a Kullback-Leibler divergence loss is employed to gradually guide the model towards the calibrated distance-based distribution. Extensive evaluations on eight target domains show that this target ranking calibration process can improve conventional distance-based classifiers in few-shot learning.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). Builds on 32 of its 56 references that are in the map. First posted on arXiv 1 Dec 2021.

Builds on

32 of 56 references.

References · 32

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  2. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  3. 2016Matching Networks for One Shot Learningcited by 2,255
  4. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  5. 2019A Closer Look at Few-shot Classificationcited by 684
  6. 2021Domain Generalization with MixStylecited by 566
  7. 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
  8. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 437
  9. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  10. 2017Re-ranking Person Re-identification with k-reciprocal Encodingcited by 262
  11. 2019Hyperbolic Image Embeddingscited by 221
  12. 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 211
20 more
  1. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 185
  2. 2021Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillationcited by 134
  3. 2020Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustnesscited by 121
  4. 2020High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identificationcited by 106
  5. 2019TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learningcited by 91
  6. 2020Self-training for Few-shot Transfer Across Extreme Task Differencescited by 76
  7. 2017A Pose-Sensitive Embedding for Person Re-Identification with Expanded Cross Neighborhood Re-Rankingcited by 74
  8. 2020A Universal Representation Transformer Layer for Few-Shot Image Classificationcited by 65
  9. 2021Cross-Domain Few-Shot Classification via Adversarial Task Augmentationcited by 63
  10. 2020Explanation-Guided Training for Cross-Domain Few-Shot Classificationcited by 58
  11. 2015Cross-domain Image Retrieval with a Dual Attribute-aware Ranking Networkcited by 53
  12. 2017Few-Shot Learning Through an Information Retrieval Lenscited by 51
  13. 2021Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencodercited by 51
  14. 2021Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Datacited by 48
  15. 2020Cross-Domain Few-Shot Learning by Representation Fusioncited by 32
  16. 2020Feature Transformation Ensemble Model with Batch Spectral Regularization for Cross-Domain Few-Shot Classificationcited by 20
  17. 2021On the Importance of Distractors for Few-Shot Classificationcited by 14
  18. 2020Large Margin Mechanism and Pseudo Query Set on Cross-Domain Few-Shot Learningcited by 8
  19. 2020Few-Shot Image Classification via Contrastive Self-Supervised Learningcited by 5
  20. 2018Adaptive Re-ranking of Deep Feature for Person Re-identificationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 9; 2024: 6; 2025: 6; 2026: 4.

27 papers.

Sort:

By area:

  1. 2023StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learningcited by 53
  2. 2023Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image Classificationcited by 30
  3. 2024Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learningcited by 26
  4. 2023Dual Adaptive Representation Alignment for Cross-domain Few-shot Learningcited by 15
  5. 2023Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Surveycited by 14
  6. 2024Enhancing Information Maximization with Distance-Aware Contrastive Learning for Source-Free Cross-Domain Few-Shot Learningcited by 13
  7. 2024Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learningcited by 11
  8. 2022ME-D2N: Multi-Expert Domain Decompositional Network for Cross-Domain Few-Shot Learningcited by 9
  9. 2024Towards Few-Shot Learning in the Open World: A Review and Beyondcited by 5
  10. 2024Step-wise Distribution Alignment Guided Style Prompt Tuning for Source-free Cross-domain Few-shot Learningcited by 5
  11. 2022Cross-Domain Few-Shot Classification via Inter-Source Stylizationcited by 4
  12. 2024Exploring the Common Appearance-Boundary Adaptation for Nighttime Optical Flowcited by 4
15 more
  1. 2025Random Registers for Cross-Domain Few-Shot Learningcited by 4
  2. 2023A Survey of Deep Visual Cross-Domain Few-Shot Learningcited by 3
  3. 2025Revisiting Continuity of Image Tokens for Cross-domain Few-shot Learningcited by 3
  4. 2023Improving Cross-domain Few-shot Classification with Multilayer Perceptroncited by 2
  5. 2025Free Lunch to Meet the Gap: Intermediate Domain Reconstruction for Cross-Domain Few-Shot Learningcited by 2
  6. 2023Adaptive Semantic Consistency for Cross-domain Few-shot Classificationcited by 1
  7. 2026Improving CLIP Adaptation by Breaking Tail Alignment for Source-Free Cross-Domain Few-Shot Learningcited by 1
  8. 2023Plug-and-Play Feature Generation for Few-Shot Medical Image Classificationcited by 0
  9. 2023Adaptive Weighted Co-Learning for Cross-Domain Few-Shot Learningcited by 0
  10. 2025Semantic-Anchored, Class Variance-Optimized Clustering for Robust Semi-Supervised Few-Shot Learningcited by 0
  11. 2025A Cross-Domain Few-Shot Learning Method Based on Domain Knowledge Mappingcited by 0
  12. 2025FreqGRL: Suppressing Low-Frequency Bias and Mining High-Frequency Knowledge for Cross-Domain Few-Shot Learningcited by 0
  13. 2026SRasP: Self-Reorientation Adversarial Style Perturbation for Cross-Domain Few-Shot Learningcited by 0
  14. 2026When Semantics Saturate or Emerge: Adaptation-Conditional Semantic Utility in Source-Free Cross-Domain Few-Shot Learningcited by 0
  15. 2026Are We Really Doing Few-Shot Learning? A Critical Examination of Pre-Training Assumptionscited by 0