{"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/simaug-learning-robust-representations-from-1","title":"SimAug: Learning Robust Representations from Simulation for Trajectory Prediction","arxiv_id":null,"date":"2020-08-01","proceeding":"ECCV 2020 8","authors":["Junwei Liang","Lu Jiang","Alexander Hauptmann"],"abstract":"This paper studies the problem of predicting future trajectories of people in unseen cameras of novel scenarios and views. We approach this problem through the real-data-free setting in which the model is trained only on 3D simulation data and applied out-of-the-box to a wide variety of real cameras. We propose a novel approach to learn robust representation through augmenting the simulation training data such that the representation can better generalize to unseen real-world test data. The key idea is to mix the feature of the hardest camera view with the adversarial feature of the original view. We refer to our method as $ extit{SimAug}$. We show that $ extit{SimAug}$ achieves promising results on three real-world benchmarks using zero real training data, and state-of-the-art performance in the Stanford Drone and the VIRAT/ActEV dataset when using in-domain training data. Code and models are released at https://next.cs.cmu.edu/simaug","url_abs":"https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/1850_ECCV_2020_paper.php","url_pdf":"https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123580273.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":"simaug-learning-robust-representations-from-1","repo_url":"https://github.com/JunweiLiang/Multiverse","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"adversarial-attack","task_name":"Adversarial Attack"},{"task_slug":"adversarial-defense","task_name":"Adversarial Defense"},{"task_slug":"pedestrian-trajectory-prediction","task_name":"Pedestrian Trajectory Prediction"},{"task_slug":"trajectory-forecasting","task_name":"Trajectory Forecasting"},{"task_slug":"trajectory-prediction","task_name":"Trajectory Prediction"}],"methods":[{"method_slug":"simaug","method_name":"SimAug"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/trajectory-forecasting-on-actev","task":"Trajectory Forecasting","dataset":"ActEV","model":"SimAug","rank_in_archive_order":1,"of":2,"metrics":{"ADE-8/12":"17.96"},"uses_additional_data":false},{"leaderboard":"/sota/trajectory-forecasting-on-stanford-drone","task":"Trajectory Forecasting","dataset":"Stanford Drone","model":"SimAug","rank_in_archive_order":1,"of":1,"metrics":{"ADE-8/12 @K = 20":"10.27"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}