用草图实现少样本关键点检测，无需源数据即可快速适应新任务。
Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection
- 基于原型框架与网格定位器，融合草图与图像特征。
- 在新关键点和新类别上均实现少样本快速收敛。
- 适合无标注数据、需快速适配新任务的场景。
关键点检测是现代机器感知的核心任务，但在少样本学习中面临挑战，尤其当查询数据与源数据分布不一致时。本文提出利用草图这一人类表达形式作为无源数据替代方案。针对跨模态嵌入难对齐和用户草图风格差异问题，设计了基于原型的框架，结合网格定位器与原型域自适应方法。通过大量实验验证，该方法在新关键点和新类别上均实现了高效的少样本收敛，有效解决了无源数据下的少样本关键点检测难题。
原文摘要 · Abstract (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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。