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

Abstract

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.

Cite

Text

Maity et al. "Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection." International Conference on Computer Vision, 2025.

Markdown

[Maity et al. "Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection." International Conference on Computer Vision, 2025.](https://mlanthology.org/iccv/2025/maity2025iccv-doodle/)

BibTeX

@inproceedings{maity2025iccv-doodle,
  title     = {{Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection}},
  author    = {Maity, Subhajit and Bhunia, Ayan Kumar and Koley, Subhadeep and Chowdhury, Pinaki Nath and Sain, Aneeshan and Song, Yi-Zhe},
  booktitle = {International Conference on Computer Vision},
  year      = {2025},
  pages     = {284-296},
  url       = {https://mlanthology.org/iccv/2025/maity2025iccv-doodle/}
}