{"url":"/method/cbnet","slug":"cbnet","name":"CBNet","full_name":"Composite Backbone Network","full_name_withheld":false,"description_markdown":"**CBNet** is a backbone architecture that consists of multiple identical backbones (specially called Assistant Backbones and Lead Backbone) and composite connections between neighbor backbones. From left to right, the output of each stage in an Assistant Backbone, namely higher-level\r\nfeatures, flows to the parallel stage of the succeeding backbone as part of inputs through composite connections. Finally, the feature maps of the last backbone named Lead\r\nBackbone are used for object detection. The features extracted by CBNet for object detection fuse the high-level and low-level features of multiple backbones, hence improve the detection performance.","description_state":"present","introduced_year":null,"introduced_by":{"title":"CBNet: A Novel Composite Backbone Network Architecture for Object Detection","paper":"/paper/cbnet-a-novel-composite-backbone-network","first_author":"Yudong Liu","n_authors":7,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/cbnet-a-novel-composite-backbone-network"},"source":{"url":"https://arxiv.org/abs/1909.03625v1","title":"CBNet: A Novel Composite Backbone Network Architecture for Object Detection","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":"Backbone Architectures","url":"/methods/category/backbone-architectures","pwc_aliases":[]}],"n_papers_tagged":3,"archive_num_papers":3,"papers_newest_first":[{"paper":null,"title":"A Converting Autoencoder Toward Low-latency and Energy-efficient DNN Inference at the Edge","date":"2024-03-11","arxiv_id":"2403.07036","n_code_links":0,"syntology":null},{"paper":null,"title":"Parallel Pre-trained Transformers (PPT) for Synthetic Data-based Instance Segmentation","date":"2022-06-22","arxiv_id":"2206.10845","n_code_links":0,"syntology":null},{"paper":"/paper/cbnet-a-novel-composite-backbone-network","title":"CBNet: A Novel Composite Backbone Network Architecture for Object Detection","date":"2019-09-09","arxiv_id":"1909.03625","n_code_links":6,"syntology":{"ran":0,"of":4,"unverified":4,"pointer_only":1}}],"papers_shown":3,"tasks":[{"task":"/task/instance-segmentation","name":"Instance Segmentation","papers":2},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":2},{"task":null,"name":"GPU","papers":1},{"task":"/task/image-classification","name":"Image Classification","papers":1},{"task":"/task/object-detection","name":"Object Detection","papers":1},{"task":"/task/raspberry-pi-4","name":"Raspberry Pi 4","papers":1},{"task":"/task/segmentation","name":"Segmentation","papers":1},{"task":"/task/image-classification","name":"image-classification","papers":1},{"task":"/task/object-detection-1","name":"object-detection","papers":1}],"tasks_shown":9,"n_tasks":9,"usage_by_year":[{"year":"2019","papers":1},{"year":"2022","papers":1},{"year":"2024","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/cbnet"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}