Dynamic Input Structure and Network Assembly for Few-Shot Learning
This addresses a practical bottleneck for deploying few-shot learning in production systems, but appears incremental as it focuses on input flexibility rather than core learning performance.
The paper tackles the problem of few-shot learning requiring fixed-size inputs, which limits practical utility when class sizes vary, by proposing an approach to construct and train a network that dynamically handles arbitrary example sizes.
The ability to learn from a small number of examples has been a difficult problem in machine learning since its inception. While methods have succeeded with large amounts of training data, research has been underway in how to accomplish similar performance with fewer examples, known as one-shot or more generally few-shot learning. This technique has been shown to have promising performance, but in practice requires fixed-size inputs making it impractical for production systems where class sizes can vary. This impedes training and the final utility of few-shot learning systems. This paper describes an approach to constructing and training a network that can handle arbitrary example sizes dynamically as the system is used.