Bridging Domain Expertise and Generalization for Performance Estimation
弥合领域专业知识与泛化能力以实现性能估计
机构 * School of Computer Science and Engineering, Sun Yat-sen University, China(中山大学计算机科学与工程学院) ; Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, China(教育部人工智能与先进计算重点实验室) ; Shenzhen Loop Area Institute, China(深圳环湖院) ; Alibaba Cloud(阿里云)
AI总结 提出FRAP方法,利用外部基础模型和基础模型的互补优势,通过温度缩放校准和对齐预测分布,构建更可靠的伪标签参考分布,从而在分布偏移下准确估计模型性能。