English

ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic

Computer Vision and Pattern Recognition 2022-04-01 v2 Artificial Intelligence Computation and Language

Abstract

Recent text-to-image matching models apply contrastive learning to large corpora of uncurated pairs of images and sentences. While such models can provide a powerful score for matching and subsequent zero-shot tasks, they are not capable of generating caption given an image. In this work, we repurpose such models to generate a descriptive text given an image at inference time, without any further training or tuning steps. This is done by combining the visual-semantic model with a large language model, benefiting from the knowledge in both web-scale models. The resulting captions are much less restrictive than those obtained by supervised captioning methods. Moreover, as a zero-shot learning method, it is extremely flexible and we demonstrate its ability to perform image arithmetic in which the inputs can be either images or text, and the output is a sentence. This enables novel high-level vision capabilities such as comparing two images or solving visual analogy tests. Our code is available at: https://github.com/YoadTew/zero-shot-image-to-text.

Keywords

Cite

@article{arxiv.2111.14447,
  title  = {ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic},
  author = {Yoad Tewel and Yoav Shalev and Idan Schwartz and Lior Wolf},
  journal= {arXiv preprint arXiv:2111.14447},
  year   = {2022}
}

Comments

To appear in CVPR'22

R2 v1 2026-06-24T07:55:29.258Z