{"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/two-level-data-augmentation-for-calibrated","title":"Two-level Data Augmentation for Calibrated Multi-view Detection","arxiv_id":"2210.10756","date":"2022-10-19","proceeding":null,"authors":["Martin Engilberge","Haixin Shi","Zhiye Wang","Pascal Fua"],"abstract":"Data augmentation has proven its usefulness to improve model generalization and performance. While it is commonly applied in computer vision application when it comes to multi-view systems, it is rarely used. Indeed geometric data augmentation can break the alignment among views. This is problematic since multi-view data tend to be scarce and it is expensive to annotate. In this work we propose to solve this issue by introducing a new multi-view data augmentation pipeline that preserves alignment among views. Additionally to traditional augmentation of the input image we also propose a second level of augmentation applied directly at the scene level. When combined with our simple multi-view detection model, our two-level augmentation pipeline outperforms all existing baselines by a significant margin on the two main multi-view multi-person detection datasets WILDTRACK and MultiviewX.","url_abs":"https://arxiv.org/abs/2210.10756v1","url_pdf":"https://arxiv.org/pdf/2210.10756v1.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":"two-level-data-augmentation-for-calibrated","repo_url":"https://github.com/cvlab-epfl/mvaug","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"human-detection","task_name":"Human Detection"},{"task_slug":"two","task_name":"Vocal Bursts Valence Prediction"},{"task_slug":null,"task_name":"multi-view detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.10756","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}