Comparison of Vision-Language Model (VLM) Pre-training Methods under Zero-Shot Image Classification Settings
收藏DataCite Commons2025-11-24 更新2026-05-04 收录
下载链接：
https://orkg.org/comparison/R1564676
下载链接
链接失效反馈官方服务：
资源简介：
Compares various vision-language model (VLM) pre-training approaches evaluated in zero-shot image classification settings. It highlights differences in training strategies, datasets, and performance, illustrating how pre-training objectives influence generalization to unseen image-text pairs.
提供机构：
Open Research Knowledge Graph
创建时间：
2025-11-24
