mlsanityData to 7 Oct 2026

Iterative label cleaning for transductive and semi-supervised few-shot learning

arXiv 2012.07962 ↗First posted 14 Dec 2020cs.LG cs.AI cs.CVcited by 40

Not on the map. Why?

Abstract (arXiv)

Few-shot learning amounts to learning representations and acquiring knowledge such that novel tasks may be solved with both supervision and data being limited. Improved performance is possible by transductive inference, where the entire test set is available concurrently, and semi-supervised learning, where more unlabeled data is available. Focusing on these two settings, we introduce a new algorithm that leverages the manifold structure of the labeled and unlabeled data distribution to predict pseudo-labels, while balancing over classes and using the loss value distribution of a limited-capacity classifier to select the cleanest labels, iteratively improving the quality of pseudo-labels. Our solution surpasses or matches the state of the art results on four benchmark datasets, namely miniImageNet, tieredImageNet, CUB and CIFAR-FS, while being robust over feature space pre-processing and the quantity of available data. The publicly available source code can be found in https://github.com/MichalisLazarou/iLPC.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 10; 2023: 14; 2024: 5; 2025: 6; 2026: 2.

40 papers.

Sort:

By area:

  1. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  2. 2024Boosting Vision-Language Models with Transductioncited by 36
  3. 2024Transductive Zero-Shot and Few-Shot CLIPcited by 31
  4. 2023Transductive Few-shot Learning with Prototype-based Label Propagation by Iterative Graph Refinementcited by 30
  5. 2022EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredientscited by 15
  6. 2025Enhancing CLIP Robustness via Cross-Modality Alignmentcited by 14
  7. 2025Dynamic Multimodal Prototype Learning in Vision-Language Modelscited by 13
  8. 2023HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognitioncited by 12
  9. 2021Label Hallucination for Few-Shot Classificationcited by 11
  10. 2023Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-shot Learning with Hyperspherical Embeddingscited by 11
  11. 2022Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classificationcited by 10
  12. 2022An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learningcited by 10
28 more
  1. 2023Open-Set Likelihood Maximization for Few-Shot Learningcited by 10
  2. 2022Towards Practical Few-Shot Query Sets: Transductive Minimum Description Length Inferencecited by 9
  3. 2023Prototypes-oriented Transductive Few-shot Learning with Conditional Transportcited by 8
  4. 2026Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigationcited by 7
  5. 2021Tensor feature hallucination for few-shot learningcited by 6
  6. 2022GCT: Graph Co-Training for Semi-Supervised Few-Shot Learningcited by 5
  7. 2024A separability-based approach to quantifying generalization: which layer is best?cited by 5
  8. 2022Pseudo-Labeling Based Practical Semi-Supervised Meta-Training for Few-Shot Learningcited by 4
  9. 2023Adaptive manifold for imbalanced transductive few-shot learningcited by 4
  10. 2023DAC-MR: Data Augmentation Consistency Based Meta-Regularization for Meta-Learningcited by 4
  11. 2022PLATINUM: Semi-Supervised Model Agnostic Meta-Learning using Submodular Mutual Informationcited by 3
  12. 2022TransBoost: Improving the Best ImageNet Performance using Deep Transductioncited by 3
  13. 2023A Survey of Historical Learning: Learning Models with Learning Historycited by 3
  14. 2023PrototypeFormer: Learning to Explore Prototype Relationships for Few-shot Image Classificationcited by 3
  15. 2022Model-Agnostic Few-Shot Open-Set Recognitioncited by 2
  16. 2023Polarity is all you need to learn and transfer fastercited by 2
  17. 2021Few-shot learning via tensor hallucinationcited by 1
  18. 2024UNEM: UNrolled Generalized EM for Transductive Few-Shot Learningcited by 1
  19. 2025Transductive One-Shot Learning Meet Subspace Decompositioncited by 1
  20. 2026GuardAlign: Test-time Safety Alignment in Multimodal Large Language Modelscited by 1
  21. 2023Few-shot Image Classification based on Gradual Machine Learningcited by 0
  22. 2023Language-Guided Reinforcement Learning for Hard Attention in Few-Shot Learningcited by 0
  23. 2023Adaptive Anchor Label Propagation for Transductive Few-Shot Learningcited by 0
  24. 2023Robust Transductive Few-shot Learning via Joint Message Passing and Prototype-based Soft-label Propagationcited by 0
  25. 2024Improving 3D Few-Shot Segmentation with Inference-Time Pseudo-Labelingcited by 0
  26. 2025Semantic-Anchored, Class Variance-Optimized Clustering for Robust Semi-Supervised Few-Shot Learningcited by 0
  27. 2025Decision Boundary Optimization-Informed Domain Adaptationcited by 0
  28. 2025Advancing Cache-Based Few-Shot Classification via Patch-Driven Relational Gated Graph Attentioncited by 0