ProMi：一种面向带边界框标注的少样本分割的高效原型混合基线
ProMi: An Efficient Prototype-Mixture Baseline for Few-Shot Segmentation with Bounding-Box Annotations
AI总结：
针对机器人场景中少样本分割像素级标注成本高的问题，提出无需训练的ProMi原型混合方法，用边界框标注实现背景分布混合建模，在多数据集上取得最优效果并适配真实移动机器人任务。
摘要：
在机器人应用中，少样本分割至关重要，因为它能让机器人用极少的训练数据执行复杂任务，助力其适应多样的真实世界环境。然而，即便仅对少量图像进行像素级标注，也极为耗时且成本高昂。本文提出一种新颖的少样本二值分割方法，该方法采用边界框标注而非像素级标签。我们推出了ProMi（一种高效的基于原型混合的方法），它将背景类别视为多种分布的混合体。我们的方法简单、无需训练且效果出色，可轻松适配粗粒度标注。与现有基线相比，ProMi在不同数据集上均取得了最优结果，提升幅度显著，证明了其有效性。此外，我们开展了针对真实世界移动机器人任务的定性实验，证明了我们的方法在此类场景中的适用性。我们的代码位于：https://github.com/ThalesGroup/promi。
英文摘要：
In robotics applications, few-shot segmentation is crucial because it allows robots to perform complex tasks with minimal training data, facilitating their adaptation to diverse, real-world environments. However, pixel-level annotations of even small amount of images is highly time-consuming and costly. In this paper, we present a novel few-shot binary segmentation method based on bounding-box annotations instead of pixel-level labels. We introduce, ProMi, an efficient prototype-mixture-based method that treats the background class as a mixture of distributions. Our approach is simple, training-free, and effective, accommodating coarse annotations with ease. Compared to existing baselines, ProMi achieves the best results across different datasets with significant gains, demonstrating its effectiveness. Furthermore, we present qualitative experiments tailored to real-world mobile robot tasks, demonstrating the applicability of our approach in such scenarios. Our code: https://github.com/ThalesGroup/promi.
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。
