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

arXiv: https://arxiv.org/abs/2012.07962 · HTML: https://mlsanity.com/paper/2012.07962/

## Key facts

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

## Built on by (most cited first, 30 of 40)

- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [Boosting Vision-Language Models with Transduction](https://mlsanity.com/paper/2406.01837/) (2024)
- [Transductive Zero-Shot and Few-Shot CLIP](https://mlsanity.com/paper/2405.18437/) (2024)
- [Transductive Few-shot Learning with Prototype-based Label Propagation by Iterative Graph Refinement](https://mlsanity.com/paper/2304.11598/) (2023)
- [EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients](https://mlsanity.com/paper/2201.09699/) (2022)
- [Enhancing CLIP Robustness via Cross-Modality Alignment](https://mlsanity.com/paper/2510.24038/) (2025)
- [Dynamic Multimodal Prototype Learning in Vision-Language Models](https://mlsanity.com/paper/2507.03657/) (2025)
- [HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognition](https://mlsanity.com/paper/2301.03330/) (2023)
- [Label Hallucination for Few-Shot Classification](https://mlsanity.com/paper/2112.03340/) (2021)
- [Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-shot Learning with Hyperspherical Embeddings](https://mlsanity.com/paper/2303.09352/) (2023)
- [Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification](https://mlsanity.com/paper/2209.08527/) (2022)
- [An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learning](https://mlsanity.com/paper/2209.13777/) (2022)
- [Open-Set Likelihood Maximization for Few-Shot Learning](https://mlsanity.com/paper/2301.08390/) (2023)
- [Towards Practical Few-Shot Query Sets: Transductive Minimum Description Length Inference](https://mlsanity.com/paper/2210.14545/) (2022)
- [Prototypes-oriented Transductive Few-shot Learning with Conditional Transport](https://mlsanity.com/paper/2308.03047/) (2023)
- [Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation](https://mlsanity.com/paper/2602.24041/) (2026)
- [Tensor feature hallucination for few-shot learning](https://mlsanity.com/paper/2106.05321/) (2021)
- [GCT: Graph Co-Training for Semi-Supervised Few-Shot Learning](https://mlsanity.com/paper/2203.07738/) (2022)
- [A separability-based approach to quantifying generalization: which layer is best?](https://mlsanity.com/paper/2405.01524/) (2024)
- [Pseudo-Labeling Based Practical Semi-Supervised Meta-Training for Few-Shot Learning](https://mlsanity.com/paper/2207.06817/) (2022)
- [Adaptive manifold for imbalanced transductive few-shot learning](https://mlsanity.com/paper/2304.14281/) (2023)
- [DAC-MR: Data Augmentation Consistency Based Meta-Regularization for Meta-Learning](https://mlsanity.com/paper/2305.07892/) (2023)
- [PLATINUM: Semi-Supervised Model Agnostic Meta-Learning using Submodular Mutual Information](https://mlsanity.com/paper/2201.12928/) (2022)
- [TransBoost: Improving the Best ImageNet Performance using Deep Transduction](https://mlsanity.com/paper/2205.13331/) (2022)
- [A Survey of Historical Learning: Learning Models with Learning History](https://mlsanity.com/paper/2303.12992/) (2023)
- [PrototypeFormer: Learning to Explore Prototype Relationships for Few-shot Image Classification](https://mlsanity.com/paper/2310.03517/) (2023)
- [Model-Agnostic Few-Shot Open-Set Recognition](https://mlsanity.com/paper/2206.09236/) (2022)
- [Polarity is all you need to learn and transfer faster](https://mlsanity.com/paper/2303.17589/) (2023)
- [Few-shot learning via tensor hallucination](https://mlsanity.com/paper/2104.09467/) (2021)
- [UNEM: UNrolled Generalized EM for Transductive Few-Shot Learning](https://mlsanity.com/paper/2412.16739/) (2024)

## 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.