Transductive Few-shot Learning with Prototype-based Label Propagation by Iterative Graph Refinement
This work addresses a key bottleneck in few-shot learning for computer vision, offering an incremental improvement over existing methods.
The paper tackles inaccurate prototype estimation and sub-optimal graph construction in transductive few-shot learning by proposing a prototype-based label propagation method with iterative graph refinement, achieving state-of-the-art performance on datasets like mini-ImageNet and CIFAR-FS.
Few-shot learning (FSL) is popular due to its ability to adapt to novel classes. Compared with inductive few-shot learning, transductive models typically perform better as they leverage all samples of the query set. The two existing classes of methods, prototype-based and graph-based, have the disadvantages of inaccurate prototype estimation and sub-optimal graph construction with kernel functions, respectively. In this paper, we propose a novel prototype-based label propagation to solve these issues. Specifically, our graph construction is based on the relation between prototypes and samples rather than between samples. As prototypes are being updated, the graph changes. We also estimate the label of each prototype instead of considering a prototype be the class centre. On mini-ImageNet, tiered-ImageNet, CIFAR-FS and CUB datasets, we show the proposed method outperforms other state-of-the-art methods in transductive FSL and semi-supervised FSL when some unlabeled data accompanies the novel few-shot task.