涂鸦你的关键点：基于草图的少样本关键点检测

摘要

关键点检测作为现代机器感知的核心环节，在少样本学习场景下面临着显著挑战，尤其是在无法获取与查询同分布源数据的情况下。针对这一局限，我们创新性地利用草图——这一广受欢迎的人类表达形式，提供了一种无需源数据的替代方案。然而，跨模态嵌入的掌握及用户特定草图风格的处理仍存在难题。我们提出的框架通过原型化设置，结合基于网格的定位器与原型域适应方法，成功克服了这些障碍。大量实验进一步验证了该框架在跨新关键点及类别的少样本收敛方面的优异表现。

English

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.

涂鸦你的关键点：基于草图的少样本关键点检测

Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection

摘要

Support