TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning
This addresses the problem of learning from few examples for machine learning systems, representing an incremental improvement over existing methods.
The paper tackles few-shot learning by proposing TapNets, which augment neural networks with task-adaptive projection to improve generalization across tasks, achieving state-of-the-art classification accuracies on Omniglot, miniImageNet, and tieredImageNet datasets.
Handling previously unseen tasks after given only a few training examples continues to be a tough challenge in machine learning. We propose TapNets, neural networks augmented with task-adaptive projection for improved few-shot learning. Here, employing a meta-learning strategy with episode-based training, a network and a set of per-class reference vectors are learned across widely varying tasks. At the same time, for every episode, features in the embedding space are linearly projected into a new space as a form of quick task-specific conditioning. The training loss is obtained based on a distance metric between the query and the reference vectors in the projection space. Excellent generalization results in this way. When tested on the Omniglot, miniImageNet and tieredImageNet datasets, we obtain state of the art classification accuracies under various few-shot scenarios.