{"url":"/method/simaug","slug":"simaug","name":"SimAug","full_name":"Simulation as Augmentation","full_name_withheld":false,"description_markdown":"**SimAug**, or **Simulation as Augmentation**, is a data augmentation method for trajectory prediction. It augments the representation such that it is robust to the variances in semantic scenes and camera views.  First, to deal with the gap between real and synthetic semantic scene, it represents each training trajectory by high-level scene semantic segmentation features, and defends the model from adversarial examples generated by whitebox attack methods. Second, to overcome the changes in camera views, it generates multiple views for the same trajectory, and encourages the model to focus on the “hardest” view to which the model has learned. The classification loss is adopted and the view with the highest loss is favored during training. Finally, the augmented trajectory is computed as a convex combination of the trajectories generated in previous steps. The trajectory prediction model is built on a multi-scale representation and the final model is trained to minimize the empirical vicinal risk over the distribution of augmented trajectories.","description_state":"present","introduced_year":null,"introduced_by":{"title":"SimAug: Learning Robust Representations from 3D Simulation for Pedestrian Trajectory Prediction in Unseen Cameras","paper":"/paper/simaug-learning-robust-representations-from","first_author":"Junwei Liang","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/simaug-learning-robust-representations-from"},"source":{"url":"https://arxiv.org/abs/2004.02022v2","title":"SimAug: Learning Robust Representations from 3D Simulation for Pedestrian Trajectory Prediction in Unseen Cameras","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Trajectory Data Augmentation","url":"/methods/category/trajectory-data-augmentation","pwc_aliases":[]},{"area":"General","area_id":"general","collection":"Adversarial Training","url":"/methods/category/adversarial-training","pwc_aliases":[]}],"n_papers_tagged":4,"archive_num_papers":4,"papers_newest_first":[{"paper":"/paper/simaug-enhancing-recommendation-with","title":"SimAug: Enhancing Recommendation with Pretrained Language Models for Dense and Balanced Data Augmentation","date":"2025-05-03","arxiv_id":"2505.01695","n_code_links":1,"syntology":null},{"paper":"/paper/joint-analysis-and-prediction-of-human","title":"From Recognition to Prediction: Analysis of Human Action and Trajectory Prediction in Video","date":"2020-11-20","arxiv_id":"2011.10670","n_code_links":4,"syntology":null},{"paper":"/paper/simaug-learning-robust-representations-from-1","title":"SimAug: Learning Robust Representations from Simulation for Trajectory Prediction","date":"2020-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/simaug-learning-robust-representations-from","title":"SimAug: Learning Robust Representations from 3D Simulation for Pedestrian Trajectory Prediction in Unseen Cameras","date":"2020-04-04","arxiv_id":"2004.02022","n_code_links":1,"syntology":null}],"papers_shown":4,"tasks":[{"task":"/task/trajectory-prediction","name":"Trajectory Prediction","papers":3},{"task":"/task/adversarial-attack","name":"Adversarial Attack","papers":2},{"task":"/task/adversarial-defense","name":"Adversarial Defense","papers":2},{"task":"/task/pedestrian-trajectory-prediction","name":"Pedestrian Trajectory Prediction","papers":2},{"task":"/task/trajectory-forecasting","name":"Trajectory Forecasting","papers":2},{"task":"/task/action-detection","name":"Action Detection","papers":1},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":1},{"task":"/task/collaborative-filtering","name":"Collaborative Filtering","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/fairness","name":"Fairness","papers":1},{"task":"/task/prediction","name":"Prediction","papers":1}],"tasks_shown":11,"n_tasks":11,"usage_by_year":[{"year":"2020","papers":3},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/simaug"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}