{"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/bottom-up-object-detection-by-grouping","title":"Bottom-up Object Detection by Grouping Extreme and Center Points","arxiv_id":"1901.08043","date":"2019-01-23","proceeding":"CVPR 2019 6","authors":["Xingyi Zhou","Jiacheng Zhuo","Philipp Krähenbühl"],"abstract":"With the advent of deep learning, object detection drifted from a bottom-up\nto a top-down recognition problem. State of the art algorithms enumerate a\nnear-exhaustive list of object locations and classify each into: object or not.\nIn this paper, we show that bottom-up approaches still perform competitively.\nWe detect four extreme points (top-most, left-most, bottom-most, right-most)\nand one center point of objects using a standard keypoint estimation network.\nWe group the five keypoints into a bounding box if they are geometrically\naligned. Object detection is then a purely appearance-based keypoint estimation\nproblem, without region classification or implicit feature learning. The\nproposed method performs on-par with the state-of-the-art region based\ndetection methods, with a bounding box AP of 43.2% on COCO test-dev. In\naddition, our estimated extreme points directly span a coarse octagonal mask,\nwith a COCO Mask AP of 18.9%, much better than the Mask AP of vanilla bounding\nboxes. Extreme point guided segmentation further improves this to 34.6% Mask\nAP.","url_abs":"http://arxiv.org/abs/1901.08043v3","url_pdf":"http://arxiv.org/pdf/1901.08043v3.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":"bottom-up-object-detection-by-grouping","repo_url":"https://github.com/xingyizhou/ExtremeNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"bottom-up-object-detection-by-grouping","repo_url":"https://github.com/DataXujing/ExtremeNet-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"keypoint-estimation","task_name":"Keypoint Estimation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"adam","method_name":"Adam"},{"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":"colorjitter","method_name":"ColorJitter"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"corner-pooling","method_name":"Corner Pooling"},{"method_slug":"cornernet","method_name":"CornerNet"},{"method_slug":"dextr","method_name":"DEXTR"},{"method_slug":"dilated-convolution","method_name":"Dilated Convolution"},{"method_slug":"extremenet","method_name":"ExtremeNet"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"hourglass-module","method_name":"Hourglass Module"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"pyramid-pooling-module","method_name":"Pyramid Pooling Module"},{"method_slug":"randomhorizontalflip","method_name":"Random Horizontal Flip"},{"method_slug":"random-resized-crop","method_name":"Random Resized Crop"},{"method_slug":"random-scaling","method_name":"Random Scaling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"soft-nms","method_name":"Soft-NMS"},{"method_slug":"stacked-hourglass-network","method_name":"Stacked Hourglass Network"}],"datasets_introduced":[],"methods_introduced":[{"slug":"extremenet","name":"ExtremeNet","full_name":"ExtremeNet"}],"results":[{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"ExtremeNet (Hourglass-104, multi-scale)","rank_in_archive_order":141,"of":220,"metrics":{"AP50":"59.6","AP75":"46.8","APL":"59.4","APM":"46.6","APS":"25.7","box AP":"43.3"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco-minival","task":"Object Detection","dataset":"COCO minival","model":"ExtremeNet (Hourglass-104, single-scale)","rank_in_archive_order":181,"of":220,"metrics":{"AP50":"55.1","AP75":"43.7","APL":"56.1","APM":"44.0","APS":"21.6","box AP":"40.3"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"ExtremeNet (Hourglass-104, multi-scale)","rank_in_archive_order":155,"of":225,"metrics":{"AP50":"60.5","AP75":"47.0","APL":"57.6","APM":"46.9","APS":"24.1","Hardware Burden":"180G","box mAP":"43.7"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"ExtremeNet (Hourglass-104, single-scale)","rank_in_archive_order":196,"of":225,"metrics":{"AP50":"55.5","AP75":"43.2","APL":"53.1","APM":"43.2","APS":"20.4","Hardware Burden":"180G","box mAP":"40.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.08043","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.08043"}},"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/xingyizhou/ExtremeNet","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DataXujing/ExtremeNet-Pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"ran_honours":1,"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":1,"repositories":1},"listed":{"samples":1,"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":"c2515898895b1abb","entry":"make_pool_layer","repo":"xingyizhou/ExtremeNet","repo_kind":"official","path":"models/ExtremeNet.py","file_url":"https://github.com/xingyizhou/ExtremeNet/blob/HEAD/models/ExtremeNet.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"c2515898895b1abb"}},{"code_sha256_prefix":"066affa4c564825f","entry":"convert_annotation","repo":"DataXujing/ExtremeNet-Pytorch","repo_kind":"listed","path":"xml2txt.py","file_url":"https://github.com/DataXujing/ExtremeNet-Pytorch/blob/HEAD/xml2txt.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"066affa4c564825f"}},{"code_sha256_prefix":"61bf3906cbd2ee87","entry":"data_parallel","repo":"xingyizhou/ExtremeNet","repo_kind":"official","path":"models/py_utils/data_parallel.py","file_url":"https://github.com/xingyizhou/ExtremeNet/blob/HEAD/models/py_utils/data_parallel.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"61bf3906cbd2ee87"}},{"code_sha256_prefix":"4d2829871f321cca","entry":"make_br_layer","repo":"xingyizhou/ExtremeNet","repo_kind":"official","path":"models/CornerNet.py","file_url":"https://github.com/xingyizhou/ExtremeNet/blob/HEAD/models/CornerNet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"4d2829871f321cca"}},{"code_sha256_prefix":"b859f01af13f1c20","entry":"make_tl_layer","repo":"xingyizhou/ExtremeNet","repo_kind":"official","path":"models/CornerNet.py","file_url":"https://github.com/xingyizhou/ExtremeNet/blob/HEAD/models/CornerNet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"b859f01af13f1c20"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}