{"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/pedestrian-synthesis-gan-generating","title":"Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond","arxiv_id":"1804.02047","date":"2018-04-05","proceeding":null,"authors":["Xi Ouyang","Yu Cheng","Yifan Jiang","Chun-Liang Li","Pan Zhou"],"abstract":"State-of-the-art pedestrian detection models have achieved great success in\nmany benchmarks. However, these models require lots of annotation information\nand the labeling process usually takes much time and efforts. In this paper, we\npropose a method to generate labeled pedestrian data and adapt them to support\nthe training of pedestrian detectors. The proposed framework is built on the\nGenerative Adversarial Network (GAN) with multiple discriminators, trying to\nsynthesize realistic pedestrians and learn the background context\nsimultaneously. To handle the pedestrians of different sizes, we adopt the\nSpatial Pyramid Pooling (SPP) layer in the discriminator. We conduct\nexperiments on two benchmarks. The results show that our framework can smoothly\nsynthesize pedestrians on background images of variations and different levels\nof details. To quantitatively evaluate our approach, we add the generated\nsamples into training data of the baseline pedestrian detectors and show the\nsynthetic images are able to improve the detectors' performance.","url_abs":"http://arxiv.org/abs/1804.02047v2","url_pdf":"http://arxiv.org/pdf/1804.02047v2.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":"pedestrian-synthesis-gan-generating","repo_url":"https://github.com/yueruchen/Pedestrian-Synthesis-GAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"pedestrian-synthesis-gan-generating","repo_url":"https://github.com/yueruchen/sppnet-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"pedestrian-detection","task_name":"Pedestrian Detection"},{"task_slug":"scene-text-recognition","task_name":"Scene Text Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-text-recognition-on-msda","task":"Scene Text Recognition","dataset":"MSDA","model":"MLDG","rank_in_archive_order":2,"of":2,"metrics":{"Average Accuracy":"19.02%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.02047","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}