轻量级文本检测框架，应对真实场景下的分布偏移问题
TextDS: Parameter-Efficient Representation Alignment for Scene Text Detection under Distribution Shifts
- 用双编码器+视觉基础模型，无需大规模预训练
- 仅490万参数即实现跨域鲁棒检测，性能媲美大模型
- 适合边缘设备部署，尤其在图像退化环境下表现突出
现实应用中，场景文本检测器不可避免地面临训练分布之外的分布偏移。以往方法依赖大规模场景文本预训练，但跨域变化与真实成像退化下的评估仍有限。本文提出TextDS，一种面向分布偏移的高效场景文本检测框架：首先设计数据高效的双编码器结构，结合视觉基础模型，摆脱对大规模预训练的依赖；其次提出分步LoRA适配（SWLoRA），通过动态早退机制实现渐进式低秩优化，有效适应特征；再次提出共子空间融合（CSF），在共享子空间中对齐并融合双分支特征，保留互补且抗偏移的信息；最后构建了包含恶劣成像条件的场景文本检测数据集，填补评估空白。实验表明，TextDS在多个场景下均取得良好性能，仅需490万可训练参数即可实现跨域及恶劣成像条件下的鲁棒检测。
原文摘要 · Abstract (English)
In real-world deployments, scene text detectors inevitably face distribution shifts beyond the training distribution. Prior work often depends on large-scale scene-text pretraining, yet evaluation under cross-domain changes and real-world imaging degradations remains limited. We propose TextDS, an efficient framework for scene text detection under distribution shifts. First, we propose a data-efficient dual-encoder design with visual foundation models, eliminating the reliance on large-scale scene-text pretraining. Second, we introduce Step-wise LoRA adaptation (SWLoRA), which performs progressive low-rank refinement with a dynamic early-exit mechanism for effective feature adaptation. Third, we propose Common Subspace Fusion (CSF) to align and fuse the two branches in a shared subspace while retaining complementary, shift-robust information. Finally, we construct adverse-condition scene text detection datasets to address the gap in evaluating under imaging degradation. Experiments show that TextDS achieves competitive performance in scene text detection, demonstrating robustness across domains and adverse imaging conditions with only 4.9M trainable parameters.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。