A Study on Representation Transfer for Few-Shot Learning
This work addresses few-shot learning for AI systems needing to adapt quickly with limited data, but it is incremental as it builds on existing transfer learning methods.
The authors tackled few-shot classification by systematically studying feature representations from various tasks, finding that more complex tasks yield better representations. They proposed using multi-task representations with feature selection and voting tricks, achieving performance comparable to state-of-the-art on benchmark datasets.
Few-shot classification aims to learn to classify new object categories well using only a few labeled examples. Transferring feature representations from other models is a popular approach for solving few-shot classification problems. In this work we perform a systematic study of various feature representations for few-shot classification, including representations learned from MAML, supervised classification, and several common self-supervised tasks. We find that learning from more complex tasks tend to give better representations for few-shot classification, and thus we propose the use of representations learned from multiple tasks for few-shot classification. Coupled with new tricks on feature selection and voting to handle the issue of small sample size, our direct transfer learning method offers performance comparable to state-of-art on several benchmark datasets.