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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Maity, Subhajit, Bhunia, Ayan Kumar, Koley, Subhadeep, Chowdhury, Pinaki Nath, Sain, Aneeshan, Song, Yi-Zhe
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912503801315328
author Maity, Subhajit
Bhunia, Ayan Kumar
Koley, Subhadeep
Chowdhury, Pinaki Nath
Sain, Aneeshan
Song, Yi-Zhe
author_facet Maity, Subhajit
Bhunia, Ayan Kumar
Koley, Subhadeep
Chowdhury, Pinaki Nath
Sain, Aneeshan
Song, Yi-Zhe
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_07994
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection
Maity, Subhajit
Bhunia, Ayan Kumar
Koley, Subhadeep
Chowdhury, Pinaki Nath
Sain, Aneeshan
Song, Yi-Zhe
Computer Vision and Pattern Recognition
I.4.0; I.4.9
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.
title Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection
topic Computer Vision and Pattern Recognition
I.4.0; I.4.9
url https://arxiv.org/abs/2507.07994