Papers › CornerNet-Lite: Efficient Keypoint Based Object Detection

CornerNet-Lite: Efficient Keypoint Based Object Detection

18 Apr 2019arXiv:1904.08900archive 2025-07-28

Hei Law, Yun Teng, Olga Russakovsky, Jia Deng

Keypoint-based methods are a relatively new paradigm in object detection, eliminating the need for anchor boxes and offering a simplified detection framework. Keypoint-based CornerNet achieves state of the art accuracy among single-stage detectors. However, this accuracy comes at high processing cost. In this work, we tackle the problem of efficient keypoint-based object detection and introduce CornerNet-Lite. CornerNet-Lite is a combination of two efficient variants of CornerNet: CornerNet-Saccade, which uses an attention mechanism to eliminate the need for exhaustively processing all pixels of the image, and CornerNet-Squeeze, which introduces a new compact backbone architecture. Together these two variants address the two critical use cases in efficient object detection: improving efficiency without sacrificing accuracy, and improving accuracy at real-time efficiency. CornerNet-Saccade is suitable for offline processing, improving the efficiency of CornerNet by 6.0x and the AP by 1.0% on COCO. CornerNet-Squeeze is suitable for real-time detection, improving both the efficiency and accuracy of the popular real-time detector YOLOv3 (34.4% AP at 30ms for CornerNet-Squeeze compared to 33.0% AP at 39ms for YOLOv3 on COCO). Together these contributions for the first time reveal the potential of keypoint-based detection to be useful for applications requiring processing efficiency.

PaperPDFCodeCode 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 27 code samples harvested from 4 repositories linked to this paper: 21 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 1 honoured, 0 violated, 20 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 10 samples from 1 repository, 6 ran (6 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 17 samples from 3 repositories, 15 ran (15 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

princeton-vl/CornerNet-Lite officialmentioned on GitHubpytorchBSD-3-ClauseSyntology: 10 samples, 6 ran (0 instrument-failed) · 4 unverified report
Arno3165229/CornerNet_Traffic_Light mentioned on GitHubpytorchBSD-3-ClauseSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
hollyprince/ObjectsDetection-CornerNet-Lite mentioned on GitHubpytorchBSD-3-ClauseSyntology: not harvested report
jason-su/UCGNet mentioned on GitHubpytorchBSD-3-ClauseSyntology: 9 samples, 8 ran (0 instrument-failed) · 1 unverified report
takooctopus/CornerNet-Lite-Tako mentioned on GitHubpytorchBSD-3-ClauseSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
PaddlePaddle/PaddleDetection paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PP-YOLOE: An evolved version of YOLO (arXiv:2203.16250; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 2 honoured, 0 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

27 samples harvested: 21 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 1 honoured, 0 violated, 20 with no contract checked; 0 where Syntology's instrument failed) · 6 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
20ran
6unverified

Licence: 0 of the 27 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 4 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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

princeton-vl/CornerNet-Lite official repository 10 samples, 6 ran (0 instrument-failed) · 4 unverified
bbox_overlaps in 20 papers core/sample/cornernet_saccade.py ran fingerprinted BSD-3-Clause (permissive) · 60533f474c215b10 · report fixture: signature a_dets:Tensor/2/float, b_dets:Tensor/2/float · returned Tensor · level recorded 2026-09-25
clip_detections core/sample/cornernet_saccade.py ran BSD-3-Clause (permissive) · c59dc8df02529bb7 · report fixture: signature border:tuple/1/int, detections:ndarray/2/float · returned tuple · level recorded 2026-09-25
draw_bboxes in 6 papers core/vis_utils.py ran BSD-3-Clause (permissive) · 53fce1a4f77b89a0 · report fixture: signature image:ndarray/3/int, bboxes:dict/0/?, font_size:float/0/float, thresh:float/0/float, colors:dict/0/? · returned ndarray · level recorded 2026-09-25
load_cfg in 17 papers core/base.py ran BSD-3-Clause (permissive) · c98d51db76f717db · report fixture: signature cfg_file:str/0/str · returned tuple · level recorded 2026-09-25
make_layer in 76 papers core/models/CornerNet_Squeeze.py ran BSD-3-Clause (permissive) · 7e951e1acd6861ce · report fixture: signature inp_dim:int/0/int, out_dim:int/0/int, modules:int/0/int · returned Sequential · level recorded 2026-09-25
make_unpool_layer core/models/CornerNet_Squeeze.py ran BSD-3-Clause (permissive) · da553b870518bd92 · report fixture: signature dim:int/0/int · returned ConvTranspose2d · level recorded 2026-09-25
cornernet core/sample/cornernet.py unverified BSD-3-Clause (permissive) · 37018977a90a808c · report
crop_image_dets core/sample/cornernet_saccade.py unverified BSD-3-Clause (permissive) · 2032e5dc001bc848 · report
load_nnet core/base.py unverified BSD-3-Clause (permissive) · 54abd86de92a09d9 · report
make_hg_layer core/models/CornerNet.py unverified BSD-3-Clause (permissive) · 8b9e0456b6d2f8e5 · report
Arno3165229/CornerNet_Traffic_Light community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
caps_loss capsulenet.py ran BSD-3-Clause (permissive) · 5d7d6657a9bda8b0 · report fixture: signature y_true:Tensor/2/float, y_pred:Tensor/2/float, x:Tensor/4/float, x_recon:Tensor/4/float, lam_recon:float/0/float · returned Tensor · level recorded 2026-09-24
make_pool_layer in 5 papers core/models/CornerNet_Squeeze_traffic_light.py ran · honoured contract BSD-3-Clause (permissive) · c2515898895b1abb · report fixture: signature dim:int/0/int · returned Sequential · level recorded 2026-09-22
make_square capsulenet.py ran fingerprinted BSD-3-Clause (permissive) · 1a49c2fd47493e3f · report fixture: signature img:ndarray/3/int, padColor:int/0/int · returned ndarray · level recorded 2026-09-24
squash in 30 papers
census: 8 implementations from 5 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
capsulelayers.py ran fingerprinted BSD-3-Clause (permissive) · 14c8e8b4bfa1bf08 · report fixture: signature inputs:Tensor/3/float, axis:int/0/int · returned Tensor · level recorded 2026-09-24
jason-su/UCGNet community (archive-listed) 9 samples, 8 ran (0 instrument-failed) · 1 unverified
adjustBox custom/II_final_cluster.py ran fingerprinted BSD-3-Clause (permissive) · 31f1bf0da9917cf2 · report fixture: signature box:list/1/int, iw:int/0/int, ih:int/0/int · returned list · level recorded 2026-09-24
cluster_method custom/II_final_cluster.py ran BSD-3-Clause (permissive) · 266fdbb0268ac59a · report fixture: signature data:ndarray/2/int, image:ndarray/3/int, idx:str/0/str, out_cluster_path:str/0/str, w:int/0/int, h:int/0/int · returned ndarray · level recorded 2026-09-24
convert in 76 papers custom/IV_2_xml2yolo.py ran BSD-3-Clause (permissive) · 16418ec4775fb6fd · report fixture: signature size:tuple/1/int, box:tuple/1/int · returned tuple · level recorded 2026-09-24
dot_Visualization custom/II_final_cluster.py ran BSD-3-Clause (permissive) · 52e2b9065925a120 · report fixture: signature img_data:ndarray/3/int, lbl_data:list/1/tuple, save_path:str/0/str, idx:str/0/str · returned ndarray · level recorded 2026-09-24
draw_bboxes in 6 papers custom/VIII_Visual.py ran BSD-3-Clause (permissive) · f6d6243a2f16050c · report fixture: signature image:ndarray/3/int, bboxes:list/1/list, font_size:float/0/float, thresh:float/0/float, colors:NoneType/0/? · returned ndarray · level recorded 2026-09-24
format_label custom/III_crop_visdrone.py ran BSD-3-Clause (permissive) · 8208f342ced40efa · report fixture: signature txt_list:list/1/str · returned ndarray · level recorded 2026-09-24
nms in 65 papers custom/VI_NMS.py ran fingerprinted BSD-3-Clause (permissive) · 7973ac6326951ada · report fixture: signature dets:ndarray/2/float, thresh:float/0/float · returned list · level recorded 2026-09-24
readClipTxt custom/V_merge_json.py ran BSD-3-Clause (permissive) · c153426da88dccd3 · report fixture: signature txt_path:str/0/str · returned dict · level recorded 2026-09-24
print_detection_eval_metrics custom/VII_MAP.py unverified BSD-3-Clause (permissive) · dee4e996bce1007b · report
takooctopus/CornerNet-Lite-Tako community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
clip_detections core/sample/cornernet_saccade.py ran BSD-3-Clause (permissive) · 12b1c3d7659ccdbf · report fixture: signature border:tuple/1/int, detections:ndarray/2/float · returned tuple · level recorded 2026-09-24
draw_bboxes in 6 papers core/vis_utils.py ran BSD-3-Clause (permissive) · d315cf6dc8591a0f · report fixture: returned ndarray · level recorded 2026-09-24
init_parallel_jobs traindagm.py ran BSD-3-Clause (permissive) · 715bd6c6d94fc031 · report fixture: signature system_config:SystemConfig/0/?, dbs:list/1/Database, queue:Queue/0/?, fn:callable/0/?, data_aug:DataAugmentation/0/? · returned list · level recorded 2026-09-24
crop_image_dets core/sample/cornernet_saccade.py unverified BSD-3-Clause (permissive) · 7ddc205848964f81 · report

Tasks

ObjectObject DetectionReal-Time Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO minival CornerNet-Saccade (Hourglass-54) APL 58.4 #152 of 220 Archive leaderboard report
Object Detection COCO minival CornerNet-Saccade (Hourglass-54) APM 44.3 #152 of 220 Archive leaderboard report
Object Detection COCO minival CornerNet-Saccade (Hourglass-54) APS 25.5 #152 of 220 Archive leaderboard report
Object Detection COCO minival CornerNet-Saccade (Hourglass-54) box AP 42.6 #152 of 220 Archive leaderboard report
Object Detection COCO minival CornerNet-Saccade (Hourglass-104) APL 57.1 #164 of 220 Archive leaderboard report
Object Detection COCO minival CornerNet-Saccade (Hourglass-104) APM 43.5 #164 of 220 Archive leaderboard report
Object Detection COCO minival CornerNet-Saccade (Hourglass-104) APS 23.8 #164 of 220 Archive leaderboard report
Object Detection COCO minival CornerNet-Saccade (Hourglass-104) box AP 41.4 #164 of 220 Archive leaderboard report
Object Detection COCO test-dev CornerNet-Saccade (Hourglass-104, multi-scale) APL 57.3 #162 of 225 Archive leaderboard report
Object Detection COCO test-dev CornerNet-Saccade (Hourglass-104, multi-scale) APM 44.6 #162 of 225 Archive leaderboard report
Object Detection COCO test-dev CornerNet-Saccade (Hourglass-104, multi-scale) APS 24.4 #162 of 225 Archive leaderboard report
Object Detection COCO test-dev CornerNet-Saccade (Hourglass-104, multi-scale) box mAP 43.2 #162 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: CornerNet-Saccade, CornerNet-Squeeze Hourglass, CornerNet-Squeeze Hourglass Module, Depthwise Fire Module

1x1 ConvolutionAdamBatch NormalizationColorJitterConvolutionCorner PoolingCornerNet-SaccadeCornerNet-SqueezeCornerNet-Squeeze HourglassCornerNet-Squeeze Hourglass ModuleDepthwise ConvolutionDepthwise Fire ModuleDepthwise Separable ConvolutionHourglass ModuleMax PoolingPointwise ConvolutionRandom Horizontal FlipRandom Resized CropReLUResidual ConnectionSigmoid ActivationSoft-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