Data for Vision Foundation DINOv2-based models outperform multi-modal CLIP-based models for classification task in a long-tail distribution

Name: Data for Vision Foundation DINOv2-based models outperform multi-modal CLIP-based models for classification task in a long-tail distribution
Creator: Zenodo
Published: 2025-10-21T09:09:26+08:00

Zenodo2026-01-29 更新2026-05-26 收录

数据链接：

https://zenodo.org/doi/10.5281/zenodo.17404710 数据链接链接失效反馈

官方服务：

资源简介：

This dataset was used to train and test the models presented in the paper Vision Foundation DINOv2-based models outperform multi-modal CLIP-based models for classification task in a long-tail distribution.

提供机构：

Zenodo

创建时间：

2025-10-21