arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.18334cs.CV
收藏

DODA:通过扩散在实时动态农业环境中适配目标检测器

DODA: Adapting Object Detectors to Dynamic Agricultural Environments in Real-Time with Diffusion

Graduate School of Agricultural and Life Sciences(农业与生命科学研究生院);The University of Tokyo(东京大学)

Shuai Xiang, Pieter M. Blok, James Burridge, Haozhou Wang, Wei Guo

AI总结:

针对农业目标检测因环境域偏移导致模型泛化受限的问题,提出基于扩散的DODA框架,可2分钟内适配新域,无需额外训练即可生成高质量数据,在小麦数据集上显著提升检测性能,降低农业检测应用门槛。

摘要:

目标检测在农业领域应用广泛,但不同环境的域偏移限制了训练模型的更广泛使用。现有域适配方法通常需要为新域重新训练模型,由于环境不断变化,这在农业应用中不切实际。本文提出DODA(农业中目标检测域适配的扩散方法),这是一种基于扩散的框架,可在仅2分钟内将检测器适配到新域。DODA整合外部域嵌入和改进的布局转图像方法,无需额外训练即可为新域生成高质量检测数据。我们在全球小麦穗检测数据集上验证了DODA的有效性,使用DODA生成的数据微调检测器在多个域上均取得显著改进。DODA为农业域适配提供了简单而强大的解决方案,降低了种植者在个性化环境中使用检测技术的障碍。代码可在https://github.com/UTokyo-FieldPhenomics-Lab/DODA获取。

英文摘要:

Object detection has wide applications in agriculture, but domain shifts of diverse environments limit the broader use of the trained models. Existing domain adaptation methods usually require retraining the model for new domains, which is impractical for agricultural applications due to constantly changing environments. In this paper, we propose DODA ($D$iffusion for $O$bject-detection $D$omain Adaptation in $A$griculture), a diffusion-based framework that can adapt the detector to a new domain in just 2 minutes. DODA incorporates external domain embeddings and an improved layout-to-image approach, allowing it to generate high-quality detection data for new domains without additional training. We demonstrate DODA's effectiveness on the Global Wheat Head Detection dataset, where fine-tuning detectors on DODA-generated data yields significant improvements across multiple domains. DODA provides a simple yet powerful solution for agricultural domain adaptation, reducing the barriers for growers to use detection in personalised environments. The code is available at https://github.com/UTokyo-FieldPhenomics-Lab/DODA.

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。

↑