{"url":"/method/iou-balanced-sampling","slug":"iou-balanced-sampling","name":"IoU-Balanced Sampling","full_name":"IoU-Balanced Sampling","full_name_withheld":false,"description_markdown":"**IoU-Balanced Sampling** is hard mining method for object detection. Suppose we need to sample $N$ negative samples from $M$ corresponding candidates. The selected probability for each sample under random sampling is:\r\n\r\n$$ p = \\frac{N}{M} $$\r\n\r\nTo raise the selected probability of hard negatives, we evenly split the sampling interval into $K$ bins according to IoU. $N$ demanded negative samples are equally distributed to each bin. Then we select samples from them uniformly. Therefore, we get the selected probability under IoU-balanced sampling:\r\n\r\n$$ p\\_{k} = \\frac{N}{K}*\\frac{1}{M\\_{k}}\\text{ , } k\\in\\left[0, K\\right)$$\r\n\r\nwhere $M\\_{k}$ is the number of sampling candidates in the corresponding interval denoted by $k$. $K$ is set to 3 by default in our experiments.\r\n\r\nThe sampled histogram with IoU-balanced sampling is shown by green color in the Figure to the right. The IoU-balanced sampling can guide the distribution of training samples close to the one of hard negatives.","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/OceanPang/Libra_R-CNN/blob/c798fdd9b97b7b44bfdcd6b50b9f08600c6d5aca/mmdet/core/bbox/samplers/iou_balanced_neg_sampler.py#L7","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Prioritized Sampling","url":"/methods/category/prioritized-sampling","pwc_aliases":[]}],"n_papers_tagged":6,"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":null,"title":"Online progressive instance-balanced sampling for weakly supervised object detection","date":"2022-06-21","arxiv_id":"2206.10324","n_code_links":0,"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":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":6,"tasks":[{"task":"/task/object-detection","name":"Object Detection","papers":4},{"task":"/task/object-detection-1","name":"object-detection","papers":4},{"task":"/task/ensemble-learning","name":"Ensemble Learning","papers":1},{"task":"/task/fire-detection","name":"Fire Detection","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/object-localization","name":"Object Localization","papers":1},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":1},{"task":"/task/weakly-supervised-object-detection","name":"Weakly Supervised Object Detection","papers":1}],"tasks_shown":10,"n_tasks":10,"usage_by_year":[{"year":"2019","papers":1},{"year":"2020","papers":1},{"year":"2021","papers":2},{"year":"2022","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/iou-balanced-sampling"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}