Mitigating Label Noise using Prompt-Based Hyperbolic Meta-Learning in Open-Set Domain Generalization
通过基于提示的双曲元学习缓解标签噪声以实现开放集领域泛化
机构 * Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院) ; Hunan University(湖南大学) ; Shanghai AI Lab(上海人工智能实验室) ; University of Hildesheim(希尔德斯海姆大学)
AI总结 本文提出HyProMeta框架,通过双曲元学习和可学习提示缓解标签噪声,提升开放集领域泛化的性能。
Comments Accepted to International Journal of Computer Vision (IJCV). The source code of this work is released at https://github.com/KPeng9510/HyProMeta