OpenworldAUC: Towards Unified Evaluation and Optimization for Open-world Prompt Tuning
OpenworldAUC: Towards Unified Evaluation and Optimization for Open-world Prompt Tuning
Prompt tuning adapts Vision-Language Models like CLIP to open-world tasks with minimal training costs. In this direction, one typical paradigm evaluates model performance separately on known classes (i.e., base domain) and unseen classes (i.e., new domain). However, real-world scenarios require models to handle inputs without prior domain knowledge. This practical challenge has spurred the development of open-world prompt tuning, which demands a unified evaluation of two stages: 1) detecting whether an input belongs to the base or new domain (P1), and 2) classifying the sample into its correct class (P2). What's more, as domain distributions are generally unknown, a proper metric should be insensitive to varying base/new sample ratios (P3). However, we find that current metrics, including HM, overall accuracy, and AUROC, fail to satisfy these three properties simultaneously. To bridge this gap, we propose OpenworldAUC, a unified metric that jointly assesses detection and classification through pairwise instance comparisons. To optimize OpenworldAUC effectively, we introduce Gated Mixture-of-Prompts (GMoP), which employs domain-specific prompts and a gating mechanism to dynamically balance detection and classification. Theoretical guarantees ensure generalization of GMoP under practical conditions. Experiments on 15 benchmarks in open-world scenarios show GMoP achieves SOTA performance on OpenworldAUC and other metrics. We release the code at https://github.com/huacong/OpenworldAUC
Cong Hua、Qianqian Xu、Zhiyong Yang、Zitai Wang、Shilong Bao、Qingming Huang
计算技术、计算机技术
Cong Hua,Qianqian Xu,Zhiyong Yang,Zitai Wang,Shilong Bao,Qingming Huang.OpenworldAUC: Towards Unified Evaluation and Optimization for Open-world Prompt Tuning[EB/OL].(2025-05-08)[2025-07-21].https://arxiv.org/abs/2505.05180.点此复制
评论