mlsanityData to 14 Oct 2026

Adaptive manifold for imbalanced transductive few-shot learning

arXiv 2304.14281 ↗First posted 27 Apr 2023cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Transductive few-shot learning algorithms have showed substantially superior performance over their inductive counterparts by leveraging the unlabeled queries. However, the vast majority of such methods are evaluated on perfectly class-balanced benchmarks. It has been shown that they undergo remarkable drop in performance under a more realistic, imbalanced setting. To this end, we propose a novel algorithm to address imbalanced transductive few-shot learning, named Adaptive Manifold. Our method exploits the underlying manifold of the labeled support examples and unlabeled queries by using manifold similarity to predict the class probability distribution per query. It is parameterized by one centroid per class as well as a set of graph-specific parameters that determine the manifold. All parameters are optimized through a loss function that can be tuned towards class-balanced or imbalanced distributions. The manifold similarity shows substantial improvement over Euclidean distance, especially in the 1-shot setting. Our algorithm outperforms or is on par with other state of the art methods in three benchmark datasets, namely miniImageNet, tieredImageNet and CUB, and three different backbones, namely ResNet-18, WideResNet-28-10 and DenseNet-121. In certain cases, our algorithm outperforms the previous state of the art by as much as 4.2%.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 36 of its 49 references that are in the map. First posted on arXiv 27 Apr 2023.

Builds on

36 of 49 references.

References · 36

  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. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
  5. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  6. 2016HyperNetworkscited by 1,027
  7. 2018On First-Order Meta-Learning Algorithmscited by 1,018
  8. 2019A Closer Look at Few-shot Classificationcited by 684
  9. 2019Meta-Learning with Implicit Gradientscited by 525
  10. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  11. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 437
  12. 2018Meta-learning with differentiable closed-form solverscited by 397
24 more
  1. 2019A Baseline for Few-Shot Image Classificationcited by 298
  2. 2019Label Propagation for Deep Semi-supervised Learningcited by 289
  3. 2017Meta Networkscited by 269
  4. 2019Few-Shot Unsupervised Image-to-Image Translationcited by 222
  5. 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 136
  6. 2020Adversarial Feature Hallucination Networks for Few-Shot Learningcited by 110
  7. 2019Prototype Rectification for Few-Shot Learningcited by 97
  8. 2020Laplacian Regularized Few-Shot Learningcited by 92
  9. 2020Embedding Propagation: Smoother Manifold for Few-Shot Classificationcited by 80
  10. 2020Leveraging the Feature Distribution in Transfer-based Few-Shot Learningcited by 74
  11. 2020Instance Credibility Inference for Few-Shot Learningcited by 57
  12. 2019Dense Classification and Implanting for Few-Shot Learningcited by 56
  13. 2019Image Deformation Meta-Networks for One-Shot Learningcited by 56
  14. 2019Few-Shot Learning via Saliency-guided Hallucination of Samplescited by 49
  15. 2019Self-Supervised Learning For Few-Shot Image Classificationcited by 44
  16. 2020Iterative label cleaning for transductive and semi-supervised few-shot learningcited by 40
  17. 2022Few-Shot Classification with Contrastive Learningcited by 31
  18. 2023Transductive Few-shot Learning with Prototype-based Label Propagation by Iterative Graph Refinementcited by 30
  19. 2022Realistic Evaluation of Transductive Few-Shot Learningcited by 27
  20. 2021Transductive Few-Shot Classification on the Oblique Manifoldcited by 23
  21. 2019Diversity Transfer Network for Few-Shot Learningcited by 15
  22. 2022Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classificationcited by 10
  23. 2021Tensor feature hallucination for few-shot learningcited by 6
  24. 2021Local Propagation for Few-Shot Learningcited by 4

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2; 2025: 1.

4 papers.

  1. 2024Towards Few-Shot Learning in the Open World: A Review and Beyondcited by 5
  2. 2024UNEM: UNrolled Generalized EM for Transductive Few-Shot Learningcited by 1
  3. 2023Robust Transductive Few-shot Learning via Joint Message Passing and Prototype-based Soft-label Propagationcited by 0
  4. 2025Unbiased Max-Min Embedding Classification for Transductive Few-Shot Learning: Clustering and Classification Are All You Needcited by 0