Skip to yearly menu bar Skip to main content

Workshop: NeurIPS 2022 Workshop on Meta-Learning

FiT: Parameter Efficient Few-shot Transfer Learning

Aliaksandra Shysheya · John Bronskill · Massimiliano Patacchiola · Sebastian Nowozin · Richard Turner


Model parameter efficiency is key for enabling few-shot learning, inexpensive model updates for personalization, and communication efficient federated learning. In this work, we develop FiLM Transfer (FiT) which combines ideas from transfer learning (fixed pretrained backbones and fine-tuned FiLM adapter layers) and meta-learning (automatically configured Naive Bayes classifiers and episodic training) to yield parameter efficient models with superior classification accuracy at low-shot. We experiment with FiT on a range of downstream datasets and show that it achieves better classification accuracy than the leading Big Transfer (BiT) algorithm at low-shot and achieves state-of-the art accuracy on the challenging VTAB-1k benchmark, with fewer than 1% of the updateable parameters.

Chat is not available.