license: apache-2.0
language:
- en
pipeline_tag: zero-shot-image-classification
tags:
- image recognition
Recognize Anything & Tag2Text
Model card for Recognize Anything Plus Model (RAM++) .
RAM++ is the next generation of RAM, which can recognize any category with high accuracy, including both predefined common categories and diverse open-set categories.
RAM++ outperforms existing SOTA image fundamental reocngition models in terms of common tag categorie, uncommon tag categories, and human-object interaction phrase.
TL;DR
Authors from the paper write in the abstract:
We present the Recognize Anything Model~(RAM): a strong foundation model for image tagging. RAM makes a substantial step for large models in computer vision, demonstrating the zero-shot ability to recognize any common category with high accuracy. By leveraging large-scale image-text pairs for training instead of manual annotations, RAM introduces a new paradigm for image tagging. We evaluate the tagging capability of RAM on numerous benchmarks and observe an impressive zero-shot performance, which significantly outperforms CLIP and BLIP. Remarkably, RAM even surpasses fully supervised models and exhibits a competitive performance compared with the Google tagging API.
BibTex and citation info
@article{zhang2023recognize,
title={Recognize Anything: A Strong Image Tagging Model},
author={Zhang, Youcai and Huang, Xinyu and Ma, Jinyu and Li, Zhaoyang and Luo, Zhaochuan and Xie, Yanchun and Qin, Yuzhuo and Luo, Tong and Li, Yaqian and Liu, Shilong and others},
journal={arXiv preprint arXiv:2306.03514},
year={2023}
}
@article{huang2023tag2text,
title={Tag2Text: Guiding Vision-Language Model via Image Tagging},
author={Huang, Xinyu and Zhang, Youcai and Ma, Jinyu and Tian, Weiwei and Feng, Rui and Zhang, Yuejie and Li, Yaqian and Guo, Yandong and Zhang, Lei},
journal={arXiv preprint arXiv:2303.05657},
year={2023}
}