Episodic-free Task Selection for Few-shot Learning
This work addresses the challenge of improving few-shot learning performance by moving beyond the standard episodic training paradigm, which is incremental but offers a novel selection mechanism.
The paper tackles the problem of few-shot learning by proposing a meta-training framework that selects episodic-free tasks for training, rather than using episodic tasks directly, and demonstrates its effectiveness on miniImageNet, tiered-ImageNet, and CIFAR-FS datasets.
Episodic training is a mainstream training strategy for few-shot learning. In few-shot scenarios, however, this strategy is often inferior to some non-episodic training strategy, e. g., Neighbourhood Component Analysis (NCA), which challenges the principle that training conditions must match testing conditions. Thus, a question is naturally asked: How to search for episodic-free tasks for better few-shot learning? In this work, we propose a novel meta-training framework beyond episodic training. In this framework, episodic tasks are not used directly for training, but for evaluating the effectiveness of some selected episodic-free tasks from a task set that are performed for training the meta-learners. The selection criterion is designed with the affinity, which measures the degree to which loss decreases when executing the target tasks after training with the selected tasks. In experiments, the training task set contains some promising types, e. g., contrastive learning and classification, and the target few-shot tasks are achieved with the nearest centroid classifiers on the miniImageNet, tiered-ImageNet and CIFAR-FS datasets. The experimental results demonstrate the effectiveness of our approach.