OpenKD: Opening Prompt Diversity for Zero- and Few-shot Keypoint Detection

TL;DR

OpenKD introduces a multimodal prompt approach for zero- and few-shot keypoint detection, leveraging diverse text prompts and large language models to improve generalization and handle unseen keypoints effectively.

Contribution

The paper presents a novel OpenKD model that supports multimodal prompts and enhances zero-shot keypoint detection by interpolating auxiliary keypoints and texts, enabling better handling of unseen prompts.

Findings

Achieves state-of-the-art results on Z-FSKD benchmarks.

Effectively handles diverse and unseen text prompts with LLM parsing.

Significantly improves spatial reasoning for novel keypoints.

Abstract

Exploiting the foundation models (e.g., CLIP) to build a versatile keypoint detector has gained increasing attention. Most existing models accept either the text prompt (e.g., ``the nose of a cat''), or the visual prompt (e.g., support image with keypoint annotations), to detect the corresponding keypoints in query image, thereby, exhibiting either zero-shot or few-shot detection ability. However, the research on taking multimodal prompt is still underexplored, and the prompt diversity in semantics and language is far from opened. For example, how to handle unseen text prompts for novel keypoint detection and the diverse text prompts like ``Can you detect the nose and ears of a cat?'' In this work, we open the prompt diversity from three aspects: modality, semantics (seen v.s. unseen), and language, to enable a more generalized zero- and few-shot keypoint detection (Z-FSKD). We propose a novel OpenKD model which leverages multimodal prototype set to support both visual and textual prompting. Further, to infer the keypoint location of unseen texts, we add the auxiliary keypoints and texts interpolated from visual and textual domains into training, which improves the spatial reasoning of our model and significantly enhances zero-shot novel keypoint detection. We also found large language model (LLM) is a good parser, which achieves over 96% accuracy to parse keypoints from texts. With LLM, OpenKD can handle diverse text prompts. Experimental results show that our method achieves state-of-the-art performance on Z-FSKD and initiates new ways to deal with unseen text and diverse texts. The source code and data are available at https://github.com/AlanLuSun/OpenKD.