Task-Adaptive Pseudo Labeling for Transductive Meta-Learning
This addresses the sample bias issue in meta-learning for researchers and practitioners, offering an incremental improvement by adapting pseudo labeling to tasks.
The paper tackles the sample bias problem in meta-learning by introducing task-adaptive pseudo labeling for transductive meta-learning, which uses label propagation to generate pseudo labels for unlabeled query sets, resulting in improved classification performance that outperforms state-of-the-art methods in 5-way 1-shot few-shot classification.
Meta-learning performs adaptation through a limited amount of support set, which may cause a sample bias problem. To solve this problem, transductive meta-learning is getting more and more attention, going beyond the conventional inductive learning perspective. This paper proposes so-called task-adaptive pseudo labeling for transductive meta-learning. Specifically, pseudo labels for unlabeled query sets are generated from labeled support sets through label propagation. Pseudo labels enable to adopt the supervised setting as it is and also use the unlabeled query set in the adaptation process. As a result, the proposed method is able to deal with more examples in the adaptation process than inductive ones, which can result in better classification performance of the model. Note that the proposed method is the first approach of applying task adaptation to pseudo labeling. Experiments show that the proposed method outperforms the state-of-the-art (SOTA) technique in 5-way 1-shot few-shot classification.