{"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/towards-good-practices-on-building-effective","title":"Towards Good Practices on Building Effective CNN Baseline Model for Person Re-identification","arxiv_id":"1807.11042","date":"2018-07-29","proceeding":null,"authors":["Fu Xiong","Yang Xiao","Zhiguo Cao","Kaicheng Gong","Zhiwen Fang","Joey Tianyi Zhou"],"abstract":"Person re-identification is indeed a challenging visual recognition task due\nto the critical issues of human pose variation, human body occlusion, camera\nview variation, etc. To address this, most of the state-of-the-art approaches\nare proposed based on deep convolutional neural network (CNN), being leveraged\nby its strong feature learning power and classification boundary fitting\ncapacity. Although the vital role towards person re-identification, how to\nbuild effective CNN baseline model has not been well studied yet. To answer\nthis open question, we propose 3 good practices in this paper from the\nperspectives of adjusting CNN architecture and training procedure. In\nparticular, they are adding batch normalization after the global pooling layer,\nexecuting identity categorization directly using only one fully-connected, and\nusing Adam as optimizer. The extensive experiments on 3 widely-used benchmark\ndatasets demonstrate that, our propositions essentially facilitate the CNN\nbaseline model to achieve the state-of-the-art performance without any other\nhigh-level domain knowledge or low-level technical trick.","url_abs":"http://arxiv.org/abs/1807.11042v1","url_pdf":"http://arxiv.org/pdf/1807.11042v1.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":"towards-good-practices-on-building-effective","repo_url":"https://github.com/xf1994/good_practices_for_person_reID","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"open-question","task_name":"Open-Ended Question Answering"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}