mlsanityData to 14 Oct 2026

Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification

arXiv 2209.08527 ↗First posted 18 Sep 2022cs.LG cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Transductive Few-Shot learning has gained increased attention nowadays considering the cost of data annotations along with the increased accuracy provided by unlabelled samples in the domain of few shot. Especially in Few-Shot Classification (FSC), recent works explore the feature distributions aiming at maximizing likelihoods or posteriors with respect to the unknown parameters. Following this vein, and considering the parallel between FSC and clustering, we seek for better taking into account the uncertainty in estimation due to lack of data, as well as better statistical properties of the clusters associated with each class. Therefore in this paper we propose a new clustering method based on Variational Bayesian inference, further improved by Adaptive Dimension Reduction based on Probabilistic Linear Discriminant Analysis. Our proposed method significantly improves accuracy in the realistic unbalanced transductive setting on various Few-Shot benchmarks when applied to features used in previous studies, with a gain of up to 6% in accuracy. In addition, when applied to balanced setting, we obtain very competitive results without making use of the class-balance artefact which is disputable for practical use cases. We also provide the performance of our method on a high performing pretrained backbone, with the reported results further surpassing the current state-of-the-art accuracy, suggesting the genericity of the proposed method.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 40 of its 59 references that are in the map. First posted on arXiv 18 Sep 2022.

Builds on

40 of 59 references.

References · 40

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  4. 2016Matching Networks for One Shot Learningcited by 2,255
  5. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  6. 2019A Closer Look at Few-shot Classificationcited by 684
  7. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  8. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  9. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  10. 2018Meta-learning with differentiable closed-form solverscited by 397
  11. 2018How to train your MAMLcited by 309
  12. 2019A Baseline for Few-Shot Image Classificationcited by 298
28 more
  1. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 294
  2. 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 195
  3. 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
  4. 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 136
  5. 2020Negative Margin Matters: Understanding Margin in Few-shot Classificationcited by 129
  6. 2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
  7. 2019Edge-labeling Graph Neural Network for Few-shot Learningcited by 114
  8. 2018Meta-Learning Probabilistic Inference For Predictioncited by 110
  9. 2019Prototype Rectification for Few-Shot Learningcited by 97
  10. 2020Laplacian Regularized Few-Shot Learningcited by 92
  11. 2020Embedding Propagation: Smoother Manifold for Few-Shot Classificationcited by 80
  12. 2020DPGN: Distribution Propagation Graph Network for Few-shot Learningcited by 79
  13. 2020Leveraging the Feature Distribution in Transfer-based Few-Shot Learningcited by 74
  14. 2021Relational Embedding for Few-Shot Classificationcited by 74
  15. 2019Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learningcited by 69
  16. 2021Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learningcited by 56
  17. 2021Rectifying the Shortcut Learning of Background for Few-Shot Learningcited by 51
  18. 2021Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learningcited by 49
  19. 2020Iterative label cleaning for transductive and semi-supervised few-shot learningcited by 40
  20. 2019A Theoretical Analysis of the Number of Shots in Few-Shot Learningcited by 39
  21. 2020TAFSSL: Task-Adaptive Feature Sub-Space Learning for few-shot classificationcited by 30
  22. 2022Realistic Evaluation of Transductive Few-Shot Learningcited by 27
  23. 2013An Information-Theoretic Analysis of Hard and Soft Assignment Methods for Clusteringcited by 17
  24. 2022EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredientscited by 16
  25. 2021Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learningcited by 14
  26. 2021Few-Shot and Continual Learning with Attentive Independent Mechanismscited by 13
  27. 2020Impact of base dataset design on few-shot image classificationcited by 9
  28. 2021Improving Classification Accuracy with Graph Filteringcited by 3

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3; 2024: 3; 2025: 3.

10 papers.

  1. 2023Prototypes-oriented Transductive Few-shot Learning with Conditional Transportcited by 8
  2. 2024Making Large Vision Language Models to be Good Few-shot Learnerscited by 7
  3. 2024BECLR: Batch Enhanced Contrastive Few-Shot Learningcited by 6
  4. 2023Adaptive manifold for imbalanced transductive few-shot learningcited by 4
  5. 2024CLCE: An Approach to Refining Cross-Entropy and Contrastive Learning for Optimized Learning Fusioncited by 4
  6. 2022A Statistical Model for Predicting Generalization in Few-Shot Classificationcited by 2
  7. 2023Robust Transductive Few-shot Learning via Joint Message Passing and Prototype-based Soft-label Propagationcited by 0
  8. 2025Unbiased Max-Min Embedding Classification for Transductive Few-Shot Learning: Clustering and Classification Are All You Needcited by 0
  9. 2025ViT-ProtoNet for Few-Shot Image Classification: A Multi-Benchmark Evaluationcited by 0
  10. 2025Object-Centric Cropping for Visual Few-Shot Classificationcited by 0