Papers › Bottom-up Object Detection by Grouping Extreme and Center Points

Bottom-up Object Detection by Grouping Extreme and Center Points

23 Jan 2019CVPR 2019 6arXiv:1901.08043archive 2025-07-28

Xingyi Zhou, Jiacheng Zhuo, Philipp Krähenbühl

With the advent of deep learning, object detection drifted from a bottom-up to a top-down recognition problem. State of the art algorithms enumerate a near-exhaustive list of object locations and classify each into: object or not. In this paper, we show that bottom-up approaches still perform competitively. We detect four extreme points (top-most, left-most, bottom-most, right-most) and one center point of objects using a standard keypoint estimation network. We group the five keypoints into a bounding box if they are geometrically aligned. Object detection is then a purely appearance-based keypoint estimation problem, without region classification or implicit feature learning. The proposed method performs on-par with the state-of-the-art region based detection methods, with a bounding box AP of 43.2% on COCO test-dev. In addition, our estimated extreme points directly span a coarse octagonal mask, with a COCO Mask AP of 18.9%, much better than the Mask AP of vanilla bounding boxes. Extreme point guided segmentation further improves this to 34.6% Mask AP.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 5 code samples harvested from 2 repositories linked to this paper: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 4 samples from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 1 sample from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

xingyizhou/ExtremeNet officialmentioned in papermentioned on GitHubpytorchBSD-3-ClauseSyntology: 4 samples, 1 ran (0 instrument-failed) · 3 unverified report
DataXujing/ExtremeNet-Pytorch mentioned on GitHubpytorchBSD-3-ClauseSyntology: 1 sample, 0 ran · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

5 samples harvested: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
4unverified

Licence: 0 of the 5 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

xingyizhou/ExtremeNet official repository 4 samples, 1 ran (0 instrument-failed) · 3 unverified
make_pool_layer in 5 papers models/ExtremeNet.py ran · honoured contract BSD-3-Clause (permissive) · c2515898895b1abb · report fixture: signature dim:int/0/int · returned Sequential · level recorded 2026-09-22
data_parallel in 13 papers models/py_utils/data_parallel.py unverified BSD-3-Clause (permissive) · 61bf3906cbd2ee87 · report
make_br_layer models/CornerNet.py unverified BSD-3-Clause (permissive) · 4d2829871f321cca · report
make_tl_layer models/CornerNet.py unverified BSD-3-Clause (permissive) · b859f01af13f1c20 · report
DataXujing/ExtremeNet-Pytorch community (archive-listed) 1 sample, 0 ran · 1 unverified
convert_annotation xml2txt.py unverified BSD-3-Clause (permissive) · 066affa4c564825f · report

Tasks

Keypoint EstimationObjectObject Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO minival ExtremeNet (Hourglass-104, multi-scale) AP50 59.6 #141 of 220 Archive leaderboard report
Object Detection COCO minival ExtremeNet (Hourglass-104, multi-scale) AP75 46.8 #141 of 220 Archive leaderboard report
Object Detection COCO minival ExtremeNet (Hourglass-104, multi-scale) APL 59.4 #141 of 220 Archive leaderboard report
Object Detection COCO minival ExtremeNet (Hourglass-104, multi-scale) APM 46.6 #141 of 220 Archive leaderboard report
Object Detection COCO minival ExtremeNet (Hourglass-104, multi-scale) APS 25.7 #141 of 220 Archive leaderboard report
Object Detection COCO minival ExtremeNet (Hourglass-104, multi-scale) box AP 43.3 #141 of 220 Archive leaderboard report
Object Detection COCO minival ExtremeNet (Hourglass-104, single-scale) AP50 55.1 #181 of 220 Archive leaderboard report
Object Detection COCO minival ExtremeNet (Hourglass-104, single-scale) AP75 43.7 #181 of 220 Archive leaderboard report
Object Detection COCO minival ExtremeNet (Hourglass-104, single-scale) APL 56.1 #181 of 220 Archive leaderboard report
Object Detection COCO minival ExtremeNet (Hourglass-104, single-scale) APM 44.0 #181 of 220 Archive leaderboard report
Object Detection COCO minival ExtremeNet (Hourglass-104, single-scale) APS 21.6 #181 of 220 Archive leaderboard report
Object Detection COCO minival ExtremeNet (Hourglass-104, single-scale) box AP 40.3 #181 of 220 Archive leaderboard report
Object Detection COCO test-dev ExtremeNet (Hourglass-104, multi-scale) AP50 60.5 #155 of 225 Archive leaderboard report
Object Detection COCO test-dev ExtremeNet (Hourglass-104, multi-scale) AP75 47.0 #155 of 225 Archive leaderboard report
Object Detection COCO test-dev ExtremeNet (Hourglass-104, multi-scale) APL 57.6 #155 of 225 Archive leaderboard report
Object Detection COCO test-dev ExtremeNet (Hourglass-104, multi-scale) APM 46.9 #155 of 225 Archive leaderboard report
Object Detection COCO test-dev ExtremeNet (Hourglass-104, multi-scale) APS 24.1 #155 of 225 Archive leaderboard report
Object Detection COCO test-dev ExtremeNet (Hourglass-104, multi-scale) Hardware Burden 180G #155 of 225 Archive leaderboard report
Object Detection COCO test-dev ExtremeNet (Hourglass-104, multi-scale) box mAP 43.7 #155 of 225 Archive leaderboard report
Object Detection COCO test-dev ExtremeNet (Hourglass-104, single-scale) AP50 55.5 #196 of 225 Archive leaderboard report
Object Detection COCO test-dev ExtremeNet (Hourglass-104, single-scale) AP75 43.2 #196 of 225 Archive leaderboard report
Object Detection COCO test-dev ExtremeNet (Hourglass-104, single-scale) APL 53.1 #196 of 225 Archive leaderboard report
Object Detection COCO test-dev ExtremeNet (Hourglass-104, single-scale) APM 43.2 #196 of 225 Archive leaderboard report
Object Detection COCO test-dev ExtremeNet (Hourglass-104, single-scale) APS 20.4 #196 of 225 Archive leaderboard report
Object Detection COCO test-dev ExtremeNet (Hourglass-104, single-scale) Hardware Burden 180G #196 of 225 Archive leaderboard report
Object Detection COCO test-dev ExtremeNet (Hourglass-104, single-scale) box mAP 40.2 #196 of 225 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: ExtremeNet

1x1 ConvolutionAdamAverage PoolingBatch NormalizationBottleneck Residual BlockColorJitterConvolutionCorner PoolingCornerNetDEXTRDilated ConvolutionExtremeNetGlobal Average PoolingHourglass ModuleKaiming InitializationMax PoolingPyramid Pooling ModuleRandom Horizontal FlipRandom Resized CropRandom ScalingReLUResidual BlockResidual ConnectionSoft-NMSStacked Hourglass Network

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections