wjpoom/SPEC

[CVPR 2024] The official implementation of paper "synthesize, diagnose, and optimize: towards fine-grained vision-language understanding"

⭐ 52 ⑂ 0 Jupyter Notebook · 2025-06-16推送

https://arxiv.org/abs/2312.00081

clip computer-vision fine-grained image-retrieval language multimodal robustness vision vision-language vision-language-model cvpr2024 compositionality text-retrieval compostional

52

Watchers

0

贡献者

0

Commits

0

Releases

0

Open Issues

2025-06-16

最近推送

原文中文

暂无 README