DropClick：面向农业机器人数据的半自动一键式分割方法
DropClick: Semi-Automated One-Click Segmentation for Agricultural Robotic Data
浏览论文内容
中文总结 AI 辅助
针对农业机器人数据标注繁琐的问题，提出半自动一键式分割工具DropClick，在SB20、BUP20数据集上表现优异，作为伪标签训练Mask2Former可节省大量输入且性能接近全点击模型。
中文摘要 AI 辅助
为视觉数据集（尤其是分割任务）标注是一项繁琐且成本高昂的工作，这阻碍了农业机器人领域的创新发展。本文提出了DropClick，一种点击引导的分割工具，可简化标注流程。该系统利用对物体的单次点击输入生成伪标签，能够替代人工标注。DropClick的独特之处在于它是一种半自动方法，无需对场景中的每个物体都进行一次点击，因此可大幅减少所需的用户输入量。我们在两个具有挑战性的农业机器人数据集SB20（用于植物分割）和BUP20（用于果实分割）上对该方法进行评估。DropClick首先使用原始训练数据中仅5张图像的小子集进行训练，随后可作为一键式分割系统部署，在SB20和BUP20上分别达到70.0和72.6的mIoU，性能与其他一键式方法相当或更优。DropClick在点击缺失（如弃权（不执行））时仍能保持高性能：当50%的点击缺失时，在SB20和BUP20上仍分别保持68.9和71.3的mIoU。我们将DropClick的输出作为伪标签，以半监督方式训练Mask2Former实例分割模型，验证其作为伪标注方法的有效性。在此过程中，减少DropClick的用户输入量后，模型性能与提供全部点击时相近：SB20的AP50为70.1 vs 70.7，BUP20的两个模型均为77.0，无差异；同时，SB20可节省46.3%的总输入，BUP20可节省31.9%的总输入。
英文摘要
Labelling vision datasets, especially for segmentation tasks, is a laborious and costly process that stymies novel developments in agricultural robotics. In this paper, we present DropClick, a click-guided segmentation tool that simplifies the annotation process. Our system utilises single-click inputs on objects to generate pseudo-labels, which can replace manual annotations. DropClick stands out as it is a semi-automated approach and does not require a click for every object in the scene. It can therefore further reduce the required amount of user input drastically. We evaluate our method on two challenging agricultural robotic datasets, SB20 and BUP20 for plant and fruit segmentation, respectively. DropClick is first trained on a small subset of just 5 images from the original training data. This DropClick model can then be deployed as a one-click segmentation system and achieves comparable or higher performance than other one-click methods achieving an mIoU of 70.0 and 72.6 points, for SB20 and BUP20 respectively. DropClick then excels at maintaining high performance when clicks are not given (e.g. dropped); when 50% of the clicks are missing it still maintains an mIoU of 68.9 and 71.3 points, for SB20 and BUP20 respectively. We validate DropClick as a pseudo-labelling approach by taking its outputs to train a Mask2Former instance-based segmentation model in a semi-supervised manner. In this process, partially removing user input from DropClick yields similar high performance when compared to providing all clicks, at 70.1 vs 70.7 points AP50 for SB20 and no difference for BUP20 at 77.0 for both models; at the same time saving 46.3% of total input for SB20 and 31.9% for BUP20.
发表机构
- University of Bonn（波恩大学）
- CSIRO（澳大利亚联邦科学与工业研究组织）
机构由 AI 辅助整理，请以论文原文为准。
