摘要: 0.多模态模型Florence: A New Foundation Model for Computer Vison; 对比loss+MLM掩码语言模型 ALBEF:Align before fuse: Vision and language representation learning with 阅读全文
posted @ 2022-06-22 21:45 哈哈哈喽喽喽 阅读(75) 评论(0) 推荐(0)