{"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/imagenet-performance-correlates-with-pose","title":"ImageNet performance correlates with pose estimation robustness and generalization on out-of-domain data","arxiv_id":null,"date":"2020-07-17","proceeding":"ICML UDL 2020 7","authors":["Alexander Mathis","Thomas Biasi","Mert Yuksekgonul","Byron Rogers","Matthias Bethge","Mackenzie Weygandt Mathis"],"abstract":"Neural networks are highly effective tools for pose estimation. However, robustness to outof-domain data remains a challenge, especially for small training sets that are common for real world applications. Here, we probe the generalization ability with three architecture classes (MobileNetV2s, ResNets, and EfficientNets). We developed a novel dataset of 30 horses that allowed\r\nfor both “within-domain” and “out-of-domain” (unseen horse) benchmarking - this is a crucial test for robustness that current human pose estimation benchmarks do not directly address. We show that better ImageNet-performing architectures perform better on both within- and out-of-domain data if they are first pretrained on ImageNet. Our results demonstrate that transfer learning is beneficial for out-of-domain robustness.","url_abs":"https://sites.google.com/view/udlworkshop2020/accepted-papers?authuser=0","url_pdf":"http://www.gatsby.ucl.ac.uk/~balaji/udl2020/accepted-papers/UDL2020-paper-047.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":"imagenet-performance-correlates-with-pose","repo_url":"https://github.com/DeepLabCut/DeepLabCut","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"LGPL-3.0"}}],"tasks":[{"task_slug":"animal-pose-estimation","task_name":"Animal Pose Estimation"},{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}