pulls together images and their textual descriptions while pushes away unmatched pairs in the feature space. (from Learning to Prompt for Vision-Language Models) 把相似的样本拉的越近越好,不同的样本越远越好!
本次分享论文:FuzzAug: Exploring Fuzzing as Data Augmentation for Neural Test Generation
基本信息
原文作者:Yifeng He, Jicheng Wang, Yuyang Rong, Hao Chen
作者单位:University of California, Davis
关键词:软件测试…