{"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/virtual-cnn-branching-efficient-feature","title":"Virtual CNN Branching: Efficient Feature Ensemble for Person Re-Identification","arxiv_id":"1803.05872","date":"2018-03-15","proceeding":null,"authors":["Albert Gong","Qiang Qiu","Guillermo Sapiro"],"abstract":"In this paper we introduce an ensemble method for convolutional neural\nnetwork (CNN), called \"virtual branching,\" which can be implemented with nearly\nno additional parameters and computation on top of standard CNNs. We propose\nour method in the context of person re-identification (re-ID). Our CNN model\nconsists of shared bottom layers, followed by \"virtual\" branches, where neurons\nfrom a block of regular convolutional and fully-connected layers are\npartitioned into multiple sets. Each virtual branch is trained with different\ndata to specialize in different aspects, e.g., a specific body region or pose\norientation. In this way, robust ensemble representations are obtained against\nhuman body misalignment, deformations, or variations in viewing angles, at\nnearly no any additional cost. The proposed method achieves competitive\nperformance on multiple person re-ID benchmark datasets, including Market-1501,\nCUHK03, and DukeMTMC-reID.","url_abs":"http://arxiv.org/abs/1803.05872v1","url_pdf":"http://arxiv.org/pdf/1803.05872v1.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":"virtual-cnn-branching-efficient-feature","repo_url":"https://github.com/agongt408/vbranch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"person-re-identification","task_name":"Person Re-Identification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}