{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/balanced-l1-loss","slug":"balanced-l1-loss","name":"Balanced L1 Loss","full_name":"Balanced L1 Loss","full_name_withheld":false,"description_markdown":"**Balanced L1 Loss** is a loss function used for the object detection task. Classification and localization problems are solved simultaneously under the guidance of a multi-task loss since\r\n[Fast R-CNN](https://paperswithcode.com/method/fast-r-cnn), defined as:\r\n\r\n$$ L\\_{p,u,t\\_{u},v} = L\\_{cls}\\left(p, u\\right) + \\lambda\\left[u \\geq 1\\right]L\\_{loc}\\left(t^{u}, v\\right) $$\r\n\r\n$L\\_{cls}$ and $L\\_{loc}$ are objective functions corresponding to recognition and localization respectively. Predictions and targets in $L\\_{cls}$ are denoted as $p$ and $u$. $t\\_{u}$ is the corresponding regression results with class $u$. $v$ is the regression target. $\\lambda$ is used for tuning the loss weight under multi-task learning. We call samples with a loss greater than or equal to 1.0 outliers. The other samples are called inliers.\r\n\r\nA natural solution for balancing the involved tasks is to tune the loss weights of them. However, owing to the unbounded regression targets, directly raising the weight of localization loss will make the model more sensitive to outliers. These outliers, which can be regarded as hard samples, will produce excessively large gradients that are harmful to the training process. The inliers, which can be regarded as the easy samples, contribute little gradient to the overall gradients compared with the outliers. To be more specific, inliers only contribute 30% gradients average per sample compared with outliers. Considering these issues, the authors introduced the balanced L1 loss, which is denoted as $L\\_{b}$.\r\n\r\nBalanced L1 loss is derived from the conventional smooth L1 loss, in which an inflection point is set to separate inliers from outliners, and clip the large gradients produced by outliers with a maximum value of 1.0, as shown by the dashed lines in the Figure to the right. The key idea of balanced L1 loss is promoting the crucial regression gradients, i.e. gradients from inliers (accurate samples), to rebalance\r\nthe involved samples and tasks, thus achieving a more balanced training within classification, overall localization and accurate localization. Localization loss $L\\_{loc}$ uses balanced L1 loss is defined as:\r\n\r\n$$ L\\_{loc} = \\sum\\_{i\\in{x,y,w,h}}L\\_{b}\\left(t^{u}\\_{i}-v\\_{i}\\right) $$\r\n\r\nThe Figure to the right shows that the balanced L1 loss increases the gradients of inliers under the control of a factor denoted as $\\alpha$. A small $\\alpha$ increases more gradient for inliers, but the gradients of outliers are not influenced. Besides, an overall promotion magnification controlled by γ is also brought in for tuning the upper bound of regression errors, which can help the objective function better balancing involved tasks. The two factors that control different aspects are mutually enhanced to reach a more balanced training.$b$ is used to ensure $L\\_{b}\\left(x = 1\\right)$ has the same value for both formulations in the equation below.\r\n\r\nBy integrating the gradient formulation above, we can get the balanced L1 loss as:\r\n\r\n$$ L\\_{b}\\left(x\\right) = \\frac{\\alpha}{b}\\left(b|x| + 1\\right)ln\\left(b|x| + 1\\right) - \\alpha|x| \\text{ if } |x| < 1$$\r\n\r\n$$ L\\_{b}\\left(x\\right) = \\gamma|x| + C \\text{ otherwise } $$\r\n\r\nin which the parameters $\\gamma$, $\\alpha$, and $b$ are constrained by $\\alpha\\text{ln}\\left(b + 1\\right) = \\gamma$. The default parameters are set as $\\alpha = 0.5$ and $\\gamma = 1.5$","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/5d6096f39b90eeafaf3457f5a39572fe5e991808/mmdet/models/losses/balanced_l1_loss.py#L9","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Loss Functions","url":"/methods/category/loss-functions","pwc_aliases":[]}],"n_papers_tagged":7,"archive_num_papers":null,"papers_newest_first":[{"paper":null,"slug":"enhancing-tree-type-detection-in-forest-fire","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","slug":"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,"slug":"fracture-detection-in-wrist-x-ray-images","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,"slug":"towards-balanced-learning-for-instance","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","slug":"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,"slug":"pbrnet-pyramidal-bounding-box-refinement-to","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","slug":"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,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":7,"with_a_code_link":3,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":7,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[],"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-l1-loss"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Balanced%20L1%20Loss","read_at":"2026-10-05T00:52:58+00:00","query":"Balanced L1 Loss","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":null,"repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'Balanced L1 Loss' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["CUDA-L1","l1-APGD","L1-Coverage","l1-AutoAttack","Weibo_Balanced","Balanced Softmax","Balanced Fitting","Balanced Robustness"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"855d4c21b1fbd5df8f42d3efeb931d45ea2de328c43408212db948e43ff7e6e5","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}