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.

翻译：少样本学习旨在学习表示并获取知识，使得在监督信息和数据均有限的情况下仍能解决新任务。通过直推推理（即同时利用整个测试集）和半监督学习（利用更多无标签数据）可提升性能。针对这两种场景，我们提出了一种新算法：该算法利用标注数据与未标注数据分布的流形结构预测伪标签，同时通过类别平衡机制，并借助有限容量分类器的损失值分布筛选最纯净的标签，迭代提升伪标签质量。我们的方法在四个基准数据集（miniImageNet、tieredImageNet、CUB和CIFAR-FS）上超越或持平当前最优结果，且对特征空间预处理及可用数据量具有鲁棒性。公开源代码详见https://github.com/MichalisLazarou/iLPC。