R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning
机构 * University of Science and Technology of China(中国科学技术大学) ; NLPR & MAIS, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所) ; University of Chinese Academy of Sciences(中国科学院大学)
专题命中 幻觉与鲁棒性 :vision-language model(title,abstract);分类 cs.CV、cs.LG
Comments CVPR 2025 (Corrected the results on the Aircraft dataset)