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


  • Huaxi Huang University of Technology Sydney
  • Junjie Zhang Shanghai University
  • Jian Zhang University of Technology Sydney
  • Qiang Wu University of Technology Sydney
  • Chang Xu The University of Sydney



Object Detection & Categorization, Transfer/Adaptation/Multi-task/Meta/Automated Learning


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.




How to Cite

Huang, H., Zhang, J., Zhang, J., Wu, Q., & Xu, C. (2021). PTN: A Poisson Transfer Network for Semi-supervised Few-shot Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 35(2), 1602-1609.



AAAI Technical Track on Computer Vision I