Complementary Text-Guided Attention for Zero-Shot Adversarial Robustness
互补文本引导注意力用于零样本对抗鲁棒性
机构 * School of Computer Science and Engineering, Tianjin University of Technology(天津理工大学计算机科学与工程学院) ; State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所多模态人工智能系统国家重点实验室) ; School of Artificial Intelligence, University of the Chinese Academy of Sciences(中国科学院大学人工智能学院)
AI总结 本文提出TGA-ZSR和Comp-TGA方法,通过局部注意力细化模块和全局注意力约束模块提升CLIP模型的零样本对抗鲁棒性,实验显示在16个数据集上分别提升9.58%和11.95%。
Comments Accepted to TPAMI 2026. arXiv admin note: substantial text overlap with arXiv:2410.21802