{"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/softer-nms-rethinking-bounding-box-regression","title":"Bounding Box Regression with Uncertainty for Accurate Object Detection","arxiv_id":"1809.08545","date":"2018-09-23","proceeding":"CVPR 2019 6","authors":["Yihui He","Chenchen Zhu","Jianren Wang","Marios Savvides","Xiangyu Zhang"],"abstract":"Large-scale object detection datasets (e.g., MS-COCO) try to define the\nground truth bounding boxes as clear as possible. However, we observe that\nambiguities are still introduced when labeling the bounding boxes. In this\npaper, we propose a novel bounding box regression loss for learning bounding\nbox transformation and localization variance together. Our loss greatly\nimproves the localization accuracies of various architectures with nearly no\nadditional computation. The learned localization variance allows us to merge\nneighboring bounding boxes during non-maximum suppression (NMS), which further\nimproves the localization performance. On MS-COCO, we boost the Average\nPrecision (AP) of VGG-16 Faster R-CNN from 23.6% to 29.1%. More importantly,\nfor ResNet-50-FPN Mask R-CNN, our method improves the AP and AP90 by 1.8% and\n6.2% respectively, which significantly outperforms previous state-of-the-art\nbounding box refinement methods. Our code and models are available at:\ngithub.com/yihui-he/KL-Loss","url_abs":"http://arxiv.org/abs/1809.08545v3","url_pdf":"http://arxiv.org/pdf/1809.08545v3.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":"softer-nms-rethinking-bounding-box-regression","repo_url":"https://github.com/yihui-he/softer-NMS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"caffe2","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"softer-nms-rethinking-bounding-box-regression","repo_url":"https://github.com/yihui-he/KL-Loss","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"caffe2","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"softer-nms-rethinking-bounding-box-regression","repo_url":"https://github.com/fiveai/saod","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"softer-nms-rethinking-bounding-box-regression","repo_url":"https://github.com/xiaoling2yy/Bounding-Box-Regression-with-Uncertainty-for-Accurate-Object-Detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"caffe2","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-localization","task_name":"Object Localization"},{"task_slug":"object-detection-1","task_name":"object-detection"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"faster-r-cnn","method_name":"Faster R-CNN"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"mask-r-cnn","method_name":"Mask R-CNN"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"roi-align","method_name":"RoIAlign"},{"method_slug":"roipool","method_name":"RoIPool"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"ResNet-50-FPN Mask R-CNN + KL Loss + var voting + soft-NMS","rank_in_archive_order":194,"of":225,"metrics":{"box mAP":"40.4"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-pascal-voc-2007","task":"Object Detection","dataset":"PASCAL VOC 2007","model":"VGG-16 + KL Loss + var voting + soft-NMS","rank_in_archive_order":21,"of":30,"metrics":{"MAP":"71.6%"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1809.08545","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.08545"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/xiaoling2yy/Bounding-Box-Regression-with-Uncertainty-for-Accurate-Object-Detection","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yihui-he/softer-NMS","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fiveai/saod","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yihui-he/KL-Loss","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"repositories":2}},"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":"867590b1664a9388","entry":"add_VGG16_conv5_body","repo":"yihui-he/KL-Loss","repo_kind":"official","path":"detectron/modeling/VGG16.py","file_url":"https://github.com/yihui-he/KL-Loss/blob/HEAD/detectron/modeling/VGG16.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"867590b1664a9388"}},{"code_sha256_prefix":"a7195f42969e79d3","entry":"add_VGG_CNN_M_1024_conv5_body","repo":"yihui-he/KL-Loss","repo_kind":"official","path":"detectron/modeling/VGG_CNN_M_1024.py","file_url":"https://github.com/yihui-he/KL-Loss/blob/HEAD/detectron/modeling/VGG_CNN_M_1024.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a7195f42969e79d3"}},{"code_sha256_prefix":"7b2d56f403fb4468","entry":"generate_anchors","repo":"yihui-he/KL-Loss","repo_kind":"official","path":"detectron/modeling/generate_anchors.py","file_url":"https://github.com/yihui-he/KL-Loss/blob/HEAD/detectron/modeling/generate_anchors.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7b2d56f403fb4468"}},{"code_sha256_prefix":"9088711bcb0a4082","entry":"qb","repo":"yihui-he/softer-NMS","repo_kind":"official","path":"detectron/utils/py_cpu_nms.py","file_url":"https://github.com/yihui-he/softer-NMS/blob/HEAD/detectron/utils/py_cpu_nms.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9088711bcb0a4082"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}