yzeng58/CoBSAT
收藏Hugging Face2024-02-29 更新2024-03-04 收录
下载链接：
https://hf-mirror.com/datasets/yzeng58/CoBSAT
下载链接
链接失效反馈官方服务：
资源简介：
---
license: mit
task_categories:
- text-to-image
language:
- en
tags:
- MLLM
- in-context learning
- text-to-image generation
- T2I-ICL
- ICL
- NLP
- natural language processing
pretty_name: CoBSAT
size_categories:
- 1K<n<10K
---
**Dataset**: The CoBSAT benchmark evaluates the ability of MLLMs to perform T2I-ICL. It covers five themes: color, background, style, action, and texture, each with two different emphases: object-inference and attribute-inference. Here, we visualize the images and their corresponding labels and captions collected for our dataset. We further integrate the images and their labels for constructing the prompts for text-to-image in-context learning using the processing code provided in https://github.com/UW-Madison-Lee-Lab/CoBSAT.
**Paper Link**: https://arxiv.org/abs/2402.01293
```tex
@article{zeng2024can,
title={Can MLLMs Perform Text-to-Image In-Context Learning?},
author={Zeng, Yuchen and Kang, Wonjun and Chen, Yicong and Koo, Hyung Il and Lee, Kangwook},
journal={arXiv preprint arXiv:2402.01293},
year={2024}
}
```
提供机构：
yzeng58
原始信息汇总
数据集概述
基本信息
- 许可证: MIT
- 任务类别: 文本到图像
- 语言: 英语
- 标签: MLLM, in-context learning, text-to-image generation, T2I-ICL, ICL, NLP, natural language processing
- 易读名称: CoBSAT
- 大小类别: 1K<n<10K
详细描述
- 数据集: CoBSAT 基准测试评估 MLLMs 执行 T2I-ICL 的能力。它涵盖五个主题：颜色、背景、风格、动作和纹理，每个主题有两个不同的重点：对象推理和属性推理。数据集包括图像及其相应的标签和说明，用于构建文本到图像的上下文学习提示。
相关文献
- 论文链接: arXiv:2402.01293
- 作者: Zeng, Yuchen; Kang, Wonjun; Chen, Yicong; Koo, Hyung Il; Lee, Kangwook
- 标题: Can MLLMs Perform Text-to-Image In-Context Learning?
- 期刊: arXiv preprint
- 年份: 2024
