Timezone: »

A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-Image Models
James Allingham · JIE REN · Michael Dusenberry · Xiuye Gu · Yin Cui · Dustin Tran · Jeremiah Liu · Balaji Lakshminarayanan

Wed Jul 26 02:00 PM -- 03:30 PM (PDT) @ Exhibit Hall 1 #302

Contrastively trained text-image models have the remarkable ability to perform zero-shot classification, that is, classifying previously unseen images into categories that the model has never been explicitly trained to identify. However, these zero-shot classifiers need prompt engineering to achieve high accuracy. Prompt engineering typically requires hand-crafting a set of prompts for individual downstream tasks. In this work, we aim to automate this prompt engineering and improve zero-shot accuracy through prompt ensembling. In particular, we ask ``Given a large pool of prompts, can we automatically score the prompts and ensemble those that are most suitable for a particular downstream dataset, without needing access to labeled validation data?". We demonstrate that this is possible. In doing so, we identify several pathologies in a naive prompt scoring method where the score can be easily overconfident due to biases in pre-training and test data, and we propose a novel prompt scoring method that corrects for the biases. Using our proposed scoring method to create a weighted average prompt ensemble, our method overall outperforms equal average ensemble, as well as hand-crafted prompts, on ImageNet, 4 of its variants, and 11 fine-grained classification benchmarks. while being fully automatic, optimization-free, and not requiring access to labeled validation data.

Author Information

James Allingham (University of Cambridge)
JIE REN (Google DeepMind)
Michael Dusenberry (Google)
Xiuye Gu (Google)
Yin Cui (Google)
Dustin Tran (Google Brain)
Jeremiah Liu (Google Research)
Balaji Lakshminarayanan (Google Brain)

More from the Same Authors