# PTN: A Poisson Transfer Network for Semi-supervised Few-shot Learning

arXiv: https://arxiv.org/abs/2012.10844 · HTML: https://mlsanity.com/paper/2012.10844/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Dec 2020.

## Built on by (most cited first, 9 of 9)

- [Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developments](https://mlsanity.com/paper/2105.08149/) (2021)
- [HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognition](https://mlsanity.com/paper/2301.03330/) (2023)
- [GCT: Graph Co-Training for Semi-Supervised Few-Shot Learning](https://mlsanity.com/paper/2203.07738/) (2022)
- [PLATINUM: Semi-Supervised Model Agnostic Meta-Learning using Submodular Mutual Information](https://mlsanity.com/paper/2201.12928/) (2022)
- [PrototypeFormer: Learning to Explore Prototype Relationships for Few-shot Image Classification](https://mlsanity.com/paper/2310.03517/) (2023)
- [A Strong Baseline for Semi-Supervised Incremental Few-Shot Learning](https://mlsanity.com/paper/2110.11128/) (2021)
- [A Maximum Log-Likelihood Method for Imbalanced Few-Shot Learning Tasks](https://mlsanity.com/paper/2211.14668/) (2022)
- [Semantic-Anchored, Class Variance-Optimized Clustering for Robust Semi-Supervised Few-Shot Learning](https://mlsanity.com/paper/2501.14401/) (2025)
- [Topology-Aware Active Learning on Graphs](https://mlsanity.com/paper/2510.25892/) (2025)

## Abstract (arXiv)

The predicament in semi-supervised few-shot learning (SSFSL) is to maximize the value of the extra unlabeled data to boost the few-shot learner. In this paper, we propose a Poisson Transfer Network (PTN) to mine the unlabeled information for SSFSL from two aspects. First, the Poisson Merriman Bence Osher (MBO) model builds a bridge for the communications between labeled and unlabeled examples. This model serves as a more stable and informative classifier than traditional graph-based SSFSL methods in the message-passing process of the labels. Second, the extra unlabeled samples are employed to transfer the knowledge from base classes to novel classes through contrastive learning. Specifically, we force the augmented positive pairs close while push the negative ones distant. Our contrastive transfer scheme implicitly learns the novel-class embeddings to alleviate the over-fitting problem on the few labeled data. Thus, we can mitigate the degeneration of embedding generality in novel classes. Extensive experiments indicate that PTN outperforms the state-of-the-art few-shot and SSFSL models on miniImageNet and tieredImageNet benchmark datasets.