Keypoint detection, integral to modern machine perception, faces challenges in few-shot learning, particularly when source data from the same distribution as the query is unavailable. This gap is addressed by leveraging sketches, a popular form of human expression, providing a source-free alternative. However, challenges arise in mastering cross-modal embeddings and handling user-specific sketch styles. Our proposed framework overcomes these hurdles with a prototypical setup, combined with a grid-based locator and prototypical domain adaptation. We also demonstrate success in few-shot convergence across novel keypoints and classes through extensive experiments.

翻译：关键点检测作为现代机器感知的核心任务，在少样本学习场景下面临显著挑战，尤其是在无法获取与查询数据同分布源数据的情况下。本文通过利用草图——一种常见的人类表达形式——提供了一种无需源数据的替代方案。然而，该方法需克服跨模态嵌入学习和用户特定草图风格处理等难题。我们提出的框架通过原型学习架构，结合基于网格的定位器与原型域自适应策略，有效解决了这些挑战。大量实验表明，该框架在新型关键点与类别的少样本收敛任务中取得了显著成功。