{"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/localization-recall-precision-lrp-a-new","title":"Localization Recall Precision (LRP): A New Performance Metric for Object Detection","arxiv_id":"1807.01696","date":"2018-07-04","proceeding":"ECCV 2018 9","authors":["Kemal Oksuz","Baris Can Cam","Emre Akbas","Sinan Kalkan"],"abstract":"Average precision (AP), the area under the recall-precision (RP) curve, is\nthe standard performance measure for object detection. Despite its wide\nacceptance, it has a number of shortcomings, the most important of which are\n(i) the inability to distinguish very different RP curves, and (ii) the lack of\ndirectly measuring bounding box localization accuracy. In this paper, we\npropose 'Localization Recall Precision (LRP) Error', a new metric which we\nspecifically designed for object detection. LRP Error is composed of three\ncomponents related to localization, false negative (FN) rate and false positive\n(FP) rate. Based on LRP, we introduce the 'Optimal LRP', the minimum achievable\nLRP error representing the best achievable configuration of the detector in\nterms of recall-precision and the tightness of the boxes. In contrast to AP,\nwhich considers precisions over the entire recall domain, Optimal LRP\ndetermines the 'best' confidence score threshold for a class, which balances\nthe trade-off between localization and recall-precision. In our experiments, we\nshow that, for state-of-the-art object (SOTA) detectors, Optimal LRP provides\nricher and more discriminative information than AP. We also demonstrate that\nthe best confidence score thresholds vary significantly among classes and\ndetectors. Moreover, we present LRP results of a simple online video object\ndetector which uses a SOTA still image object detector and show that the\nclass-specific optimized thresholds increase the accuracy against the common\napproach of using a general threshold for all classes. At\nhttps://github.com/cancam/LRP we provide the source code that can compute LRP\nfor the PASCAL VOC and MSCOCO datasets. Our source code can easily be adapted\nto other datasets as well.","url_abs":"http://arxiv.org/abs/1807.01696v2","url_pdf":"http://arxiv.org/pdf/1807.01696v2.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":"localization-recall-precision-lrp-a-new","repo_url":"https://github.com/cancam/LRP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"localization-recall-precision-lrp-a-new","repo_url":"https://github.com/kemaloksuz/aLRPLoss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"localization-recall-precision-lrp-a-new","repo_url":"https://github.com/kemaloksuz/aLRPLoss-AblationExperiments","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1807.01696","atlas_url":"https://app.syntology.ai/?focus=1807.01696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.01696"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kemaloksuz/aLRPLoss","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kemaloksuz/aLRPLoss-AblationExperiments","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cancam/LRP","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"d2840813f8bef8d7","entry":"get_output_dir","repo":"cancam/LRP","repo_kind":"official","path":"pascal-voc-lrp/utils/config.py","file_url":"https://github.com/cancam/LRP/blob/HEAD/pascal-voc-lrp/utils/config.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d2840813f8bef8d7"}},{"code_sha256_prefix":"b4096d8dc1f6bcc3","entry":"get_output_tb_dir","repo":"cancam/LRP","repo_kind":"official","path":"pascal-voc-lrp/utils/config.py","file_url":"https://github.com/cancam/LRP/blob/HEAD/pascal-voc-lrp/utils/config.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b4096d8dc1f6bcc3"}},{"code_sha256_prefix":"8a015c012f507631","entry":"unique_boxes","repo":"cancam/LRP","repo_kind":"official","path":"pascal-voc-lrp/utils/ds_utils.py","file_url":"https://github.com/cancam/LRP/blob/HEAD/pascal-voc-lrp/utils/ds_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8a015c012f507631"}},{"code_sha256_prefix":"d3e019b11b709edb","entry":"xywh_to_xyxy","repo":"cancam/LRP","repo_kind":"official","path":"pascal-voc-lrp/utils/ds_utils.py","file_url":"https://github.com/cancam/LRP/blob/HEAD/pascal-voc-lrp/utils/ds_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d3e019b11b709edb"}},{"code_sha256_prefix":"a832e5017f504280","entry":"xyxy_to_xywh","repo":"cancam/LRP","repo_kind":"official","path":"pascal-voc-lrp/utils/ds_utils.py","file_url":"https://github.com/cancam/LRP/blob/HEAD/pascal-voc-lrp/utils/ds_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a832e5017f504280"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}