超越数量：面向视觉定位的分布感知标注
Beyond Quantity: Distribution-Aware Labeling for Visual Grounding
AI总结：
提出分布感知标注框架DAL，通过双驱动标注和分布感知过滤扩展语义覆盖并提升数据质量，在三个基准上取得最先进结果。
摘要：
视觉定位需要大量且多样化的区域-文本对。然而，人工标注成本高昂，且固定词汇表限制了可扩展性和泛化能力。现有的伪标签流程往往过度拟合有偏分布，并生成噪声或冗余样本。通过对数据质量和分布覆盖的系统分析，我们发现性能提升更多来自有效的分布扩展，而非原始数据量。受此启发，我们提出了DAL，一种面向视觉定位的分布感知标注框架。该方法首先采用双驱动标注模块，其中闭集路径提供可靠的伪标签，开集路径丰富词汇并引入新概念；同时，它进一步执行显式的分布外（OOD）表达扩展以拓宽语义覆盖。然后，我们提出一个一致性和分布感知的过滤模块，以丢弃噪声或冗余的区域-文本对，并重新平衡代表性不足的语言和视觉内容，从而提高数据质量和训练效率。在三个基准上的大量实验表明，我们的方法持续优于强基线并达到最先进的结果，突显了分布感知标注在构建可扩展且稳健的视觉定位数据集中的关键作用。
英文摘要：
Visual grounding requires large and diverse region-text pairs. However, manual annotation is costly and fixed vocabularies restrict scalability and generalization. Existing pseudo-labeling pipelines often overfit to biased distributions and generate noisy or redundant samples. Through our systematic analysis of data quality and distributional coverage, we find that performance gains come less from raw data volume and more from effective distribution expansion. Motivated by this insight, we propose DAL, a distribution-aware labeling framework for visual grounding. The proposed method first employs a dual-driven annotation module, where a closed-set path provides reliable pseudo labels and an open-set path enriches vocabulary and introduces novel concepts; meanwhile, it further performs explicit out-of-distribution (OOD) expression expansion to broaden semantic coverage. We then propose a consistency- and distribution-aware filtering module to discard noisy or redundant region-text pairs and rebalance underrepresented linguistic and visual content, thereby improving both data quality and training efficiency. Extensive experiments on three benchmarks demonstrate that our method consistently outperforms strong baselines and achieves state-of-the-art results, underscoring the critical role of distribution-aware labeling in building scalable and robust visual grounding datasets.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
