{"url":"/method/balanced-feature-pyramid","slug":"balanced-feature-pyramid","name":"Balanced Feature Pyramid","full_name":"Balanced Feature Pyramid","full_name_withheld":false,"description_markdown":"**Balanced Feature Pyramid** is a feature pyramid module. It differs from approaches like [FPNs](https://paperswithcode.com/method/fpn) that integrate multi-level features using lateral connections. Instead the BFP strengthens the multi-level features using the same deeply integrated balanced semantic features. The pipeline is shown in the Figure to the right. It consists of four steps, rescaling, integrating, refining and strengthening.\r\n\r\nFeatures at resolution level $l$ are denoted as $C\\_{l}$. The number of multi-level features is denoted as $L$. The indexes of involved lowest and highest levels are denoted as $l\\_{min}$ and $l\\_{max}$. In the Figure, $C\\_{2}$ has the highest resolution. To integrate multi-level features and preserve their semantic hierarchy at the same time, we first resize the multi-level features {$C\\_{2}, C\\_{3}, C\\_{4}, C\\_{5}$} to an intermediate size, i.e., the same size as $C\\_{4}$, with interpolation and max-pooling respectively. Once the features are rescaled, the balanced semantic features are obtained by simple averaging as:\r\n\r\n$$ C = \\frac{1}{L}\\sum^{l\\_{max}}\\_{l=l\\_{min}}C\\_{l} $$\r\n\r\nThe obtained features are then rescaled using the same but reverse procedure to strengthen the original features. Each resolution obtains equal information from others in this procedure. Note that this procedure does not contain any parameter. The authors observe improvement with this nonparametric method, proving the effectiveness of the information flow. \r\n\r\nThe balanced semantic features can be further refined to be more discriminative. The authors found both the refinements with convolutions directly and the non-local module work well. But the\r\nnon-local module works in a more stable way. Therefore, embedded Gaussian non-local attention is utilized as default. The refining step helps us enhance the integrated features and further improve the results.\r\n\r\nWith this method, features from low-level to high-level are aggregated at the same time. The outputs\r\n{$P\\_{2}, P\\_{3}, P\\_{4}, P\\_{5}$} are used for object detection following the same pipeline in FPN.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"http://arxiv.org/abs/1904.02701v1","title":"Libra R-CNN: Towards Balanced Learning for Object Detection","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/open-mmlab/mmdetection/blob/ec7d83bb4c2b5ba84f198e5eb5ed491b955bce81/mmdet/models/necks/bfp.py#L10","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Feature Pyramid Blocks","url":"/methods/category/feature-pyramid-blocks","pwc_aliases":[]}],"n_papers_tagged":7,"archive_num_papers":null,"papers_newest_first":[{"paper":null,"title":"Enhancing Tree Type Detection in Forest Fire Risk Assessment: Multi-Stage Approach and Color Encoding with Forest Fire Risk Evaluation Framework for UAV Imagery","date":"2024-07-27","arxiv_id":"2407.19184","n_code_links":0,"syntology":null},{"paper":"/paper/vision-based-food-nutrition-estimation-via","title":"Vision-based Food Nutrition Estimation via RGB-D Fusion Network","date":"2023-10-25","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"Fracture Detection in Wrist X-ray Images Using Deep Learning-Based Object Detection Models","date":"2021-11-14","arxiv_id":"2111.07355","n_code_links":0,"syntology":null},{"paper":null,"title":"Towards Balanced Learning for Instance Recognition","date":"2021-08-23","arxiv_id":"2108.10175","n_code_links":0,"syntology":null},{"paper":"/paper/foodlogodet-1500-a-dataset-for-large-scale","title":"FoodLogoDet-1500: A Dataset for Large-Scale Food Logo Detection via Multi-Scale Feature Decoupling Network","date":"2021-08-10","arxiv_id":"2108.04644","n_code_links":1,"syntology":null},{"paper":null,"title":"PBRnet: Pyramidal Bounding Box Refinement to Improve Object Localization Accuracy","date":"2020-03-10","arxiv_id":"2003.04541","n_code_links":0,"syntology":null},{"paper":"/paper/libra-r-cnn-towards-balanced-learning-for","title":"Libra R-CNN: Towards Balanced Learning for Object Detection","date":"2019-04-04","arxiv_id":"1904.02701","n_code_links":6,"syntology":null}],"papers_shown":7,"tasks":[{"task":"/task/object-detection","name":"Object Detection","papers":3},{"task":"/task/object-detection-1","name":"object-detection","papers":3},{"task":"/task/ensemble-learning","name":"Ensemble Learning","papers":1},{"task":"/task/fire-detection","name":"Fire Detection","papers":1},{"task":"/task/food-recommendation","name":"Food recommendation","papers":1},{"task":"/task/fracture-detection","name":"Fracture detection","papers":1},{"task":"/task/management","name":"Management","papers":1},{"task":"/task/medical-object-detection","name":"Medical Object Detection","papers":1},{"task":"/task/nutrition","name":"Nutrition","papers":1},{"task":"/task/object-localization","name":"Object Localization","papers":1},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":1}],"tasks_shown":11,"n_tasks":11,"usage_by_year":[{"year":"2019","papers":1},{"year":"2020","papers":1},{"year":"2021","papers":3},{"year":"2023","papers":1},{"year":"2024","papers":1}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/balanced-feature-pyramid"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}