多标签实例级农业通用视觉 grounding
Multi-label Instance-level Generalised Visual Grounding in Agriculture
AI总结：
本文提出 Weed-VG 框架，通过多标签层次相关性评分和插值驱动回归，提升农业实例级视觉 grounding 能力，并提供精准农业中的 VG 方法基准。
摘要：
理解田间图像，如检测植物和区分个体作物和杂草实例，是精准农业中的核心挑战。尽管在图像-文本任务如描述生成和视觉问答方面取得了进展，但视觉 grounding（VG），即定位语言所指的物体，仍然在农业中未被探索。主要原因在于缺乏适合评估 grounding 模型在田间条件下的基准数据集，其中许多植物看起来非常相似，出现在多个尺度，且所指目标可能不在图像中。为了解决这些限制，我们引入了 gRef-CW，这是第一个为农业通用视觉 grounding 设计的数据集，包括负表达。在 gRef-CW 上基准测试当前最先进的 grounding 模型，揭示了显著的领域差距，突显了它们无法定位作物和杂草实例的能力。受这些发现的启发，我们引入了 Weed-VG，一个模块化框架，结合了多标签层次相关性评分和插值驱动的回归。Weed-VG 提升了实例级视觉 grounding 并为精准农业中的 VG 方法提供了清晰的基准。代码将在接受后发布。
英文摘要：
Understanding field imagery such as detecting plants and distinguishing individual crop and weed instances is a central challenge in precision agriculture. Despite progress in vision-language tasks like captioning and visual question answering, Visual Grounding (VG), localising language-referred objects, remains unexplored in agriculture. A key reason is the lack of suitable benchmark datasets for evaluating grounding models in field conditions, where many plants look highly similar, appear at multiple scales, and the referred target may be absent from the image. To address these limitations, we introduce gRef-CW, the first dataset designed for generalised visual grounding in agriculture, including negative expressions. Benchmarking current state-of-the-art grounding models on gRef-CW reveals a substantial domain gap, highlighting their inability to ground instances of crops and weeds. Motivated by these findings, we introduce Weed-VG, a modular framework that incorporates multi-label hierarchical relevance scoring and interpolation-driven regression. Weed-VG advances instance-level visual grounding and provides a clear baseline for developing VG methods in precision agriculture. Code will be released upon acceptance.
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。
