Multimodal Few-Shot Learning with Frozen Language Models
Abstract
When trained at sufficient scale, auto-regressive language models exhibit the notable ability to learn a new language task after being prompted with just a few examples. Here, we present a simple, yet effective, approach for transferring this few-shot learning ability to a multimodal setting (vision and language). Using aligned image and caption data, we train a vision encoder to represent each image as a sequence of continuous embeddings, such that a pre-trained, frozen language model prompted with this prefix generates the appropriate caption. The resulting system is a multimodal few-shot learner, with the surprising ability to learn a variety of new tasks when conditioned on examples, represented as a sequence of multiple interleaved image and text embeddings. We demonstrate that it can rapidly learn words for new objects and novel visual categories, do visual question-answering with only a handful of examples, and make use of outside knowledge, by measuring a single model on a variety of established and new benchmarks.
Cite
@article{arxiv.2106.13884,
title = {Multimodal Few-Shot Learning with Frozen Language Models},
author = {Maria Tsimpoukelli and Jacob Menick and Serkan Cabi and S. M. Ali Eslami and Oriol Vinyals and Felix Hill},
journal= {arXiv preprint arXiv:2106.13884},
year = {2021}
}