TextDS: Parameter-Efficient Representation Alignment for Scene Text Detection under Distribution Shifts
TextDS: 分布偏移下场景文本检测的参数高效表示对齐
机构 * School of Electrical Engineering, Xi’an Jiaotong University(西安交通大学电气工程学院) ; Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University(香港理工大学电机及电子工程学系)
AI总结 提出TextDS框架,通过视觉基础模型、逐步LoRA适应和公共子空间融合,仅用4.9M参数实现跨域和退化条件下的鲁棒场景文本检测。
Comments Accepted by ECCV 2026. Project page: https://github.com/ZChenDang/TextDS