研究人员开发了一种使用无人机图像检测 Rumex obtusifolius（一种杂草）的新方法，解决了机器学习中的域适应性挑战。标准的卷积神经网络（CNN）难以从地面数据泛化到无人机捕获的图像，但矩匹配和最大分类器差异等技术提高了性能。通过自监督学习预训练的 Vision Transformers (ViTs) 在域偏移方面表现出卓越的鲁棒性，F1 分数达到 0.8。该团队还发布了一个新的数据集 AGSMultiRumex，以促进该领域的进一步研究。 AI
影响 ViTs 在鲁棒的农业监测方面显示出潜力，可能减少杂草识别中的人工劳动。
排序理由 关于使用计算机视觉进行杂草检测的域适应技术的学术论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
Domain adaptation (DA) addresses the challenge of transferring a machine learning model trained on a source domain to a target domain with a different data distribution. In this work, we study DA for the task of Rumex obtusifolius (Rumex) image classification. We train models on …
arXiv:2604.25316v1 Announce Type: new Abstract: Domain adaptation (DA) addresses the challenge of transferring a machine learning model trained on a source domain to a target domain with a different data distribution. In this work, we study DA for the task of Rumex obtusifolius (…
Domain adaptation (DA) addresses the challenge of transferring a machine learning model trained on a source domain to a target domain with a different data distribution. In this work, we study DA for the task of Rumex obtusifolius (Rumex) image classification. We train models on …