{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/edge-weight-prediction-for-category-agnostic","title":"Edge Weight Prediction For Category-Agnostic Pose Estimation","arxiv_id":"2411.16665","date":"2024-11-25","proceeding":null,"authors":["Or Hirschorn","Shai Avidan"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2411.16665v1","url_pdf":"https://arxiv.org/pdf/2411.16665v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"edge-weight-prediction-for-category-agnostic","repo_url":"https://github.com/orhir/EdgeCape","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"2d-pose-estimation","task_name":"2D Pose Estimation"},{"task_slug":"animal-pose-estimation","task_name":"Animal Pose Estimation"},{"task_slug":"car-pose-estimation","task_name":"Car Pose Estimation"},{"task_slug":"category-agnostic-pose-estimation","task_name":"Category-Agnostic Pose Estimation"},{"task_slug":"keypoint-detection","task_name":"Keypoint Detection"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/2d-pose-estimation-on-mp-100","task":"2D Pose Estimation","dataset":"MP-100","model":"EdgeCape","rank_in_archive_order":3,"of":6,"metrics":{"Mean PCK@0.2 - 1shot":"89.01","Mean PCK@0.2 - 5shot":"92.21"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}