This work proposes POMP, a prompt pre-training method for vision-language models. Being memory and computation efficient, POMP enables the learned prompt to condense semantic information for a rich set of visual concepts with over twenty-thousand classes. Once pre-trained, the prompt with a strong transferable ability can be directly plugged into a variety of visual recognition tasks including image classification, semantic segmentation, and object detection, to boost recognition performances in a zero-shot manner. Empirical evaluation shows that POMP achieves state-of-the-art performances on 21 datasets, e.g., 67.0% average accuracy on 10 classification datasets (+3.1% compared to CoOp) and 84.4 hIoU on open-vocabulary Pascal VOC segmentation (+6.9 compared to ZSSeg). Our code is available at https://github.com/amazon-science/prompt-pretraining.
@article{arxiv.2304.04704,
title = {Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition},
author = {Shuhuai Ren and Aston Zhang and Yi Zhu and Shuai Zhang and Shuai Zheng and Mu Li and Alex Smola and Xu Sun},
journal= {arXiv preprint arXiv:2304.04704},
year = {2023}
}
Comments
Code is available at https://github.com/amazon-science/prompt-pretraining