通过预测图边权重提升跨类别姿态估计精度
Edge Weight Prediction For Category-Agnostic Pose Estimation
- 动态预测姿态图中节点间边权重，优化关键点定位
- 在100类2万+图像的MP-100上实现1次提示下最优性能
- 适合需要少样本泛化能力的视觉定位任务
类别无关姿态估计（CAPE）使用单个或少量标注支持图像，即可在多样物体类别中定位关键点。现有方法将关键点视为图中的节点，虽能缓解遮挡与对称性问题，但默认图边权重相等，限制性能。本文提出EdgeCape框架，通过预测图边权重优化定位效果。为进一步引入结构先验，设计马尔可夫结构偏差，基于节点间跳数调节自注意力交互，增强全局空间依赖建模能力。在包含100个类别、超2万张图像的MP-100基准上验证，EdgeCape在1次提示设置下达到当前最优，在5次提示设置下亦领先于同类规模方法，显著提升关键点定位准确率。代码已开源。
原文摘要 · Abstract (English)
Category-Agnostic Pose Estimation (CAPE) localizes keypoints across diverse object categories with a single model, using one or a few annotated support images. Recent works have shown that using a pose graph (i.e., treating keypoints as nodes in a graph rather than isolated points) helps handle occlusions and break symmetry. However, these methods assume a static pose graph with equal-weight edges, leading to suboptimal results. We introduce EdgeCape, a novel framework that overcomes these limitations by predicting the graph's edge weights which optimizes localization. To further leverage structural priors, we propose integrating Markovian Structural Bias, which modulates the self-attention interaction between nodes based on the number of hops between them. We show that this improves the model's ability to capture global spatial dependencies. Evaluated on the MP-100 benchmark, which includes 100 categories and over 20K images, EdgeCape achieves state-of-the-art results in the 1-shot setting and leads among similar-sized methods in the 5-shot setting, significantly improving keypoint localization accuracy. Our code is publicly available.
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。