Papers › Gradient Harmonized Single-stage Detector

Gradient Harmonized Single-stage Detector

13 Nov 2018arXiv:1811.05181archive 2025-07-28

Buyu Li, Yu Liu, Xiaogang Wang

Despite the great success of two-stage detectors, single-stage detector is still a more elegant and efficient way, yet suffers from the two well-known disharmonies during training, i.e. the huge difference in quantity between positive and negative examples as well as between easy and hard examples. In this work, we first point out that the essential effect of the two disharmonies can be summarized in term of the gradient. Further, we propose a novel gradient harmonizing mechanism (GHM) to be a hedging for the disharmonies. The philosophy behind GHM can be easily embedded into both classification loss function like cross-entropy (CE) and regression loss function like smooth-L₁ (SL₁) loss. To this end, two novel loss functions called GHM-C and GHM-R are designed to balancing the gradient flow for anchor classification and bounding box refinement, respectively. Ablation study on MS COCO demonstrates that without laborious hyper-parameter tuning, both GHM-C and GHM-R can bring substantial improvement for single-stage detector. Without any whistles and bells, our model achieves 41.6 mAP on COCO test-dev set which surpasses the state-of-the-art method, Focal Loss (FL) + SL₁, by 0.8.

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

The archive's official repository (libuyu/GHM_Detection) was not harvested; the 1 sample below comes from 1 community repository.

Syntology 1 code sample harvested from 1 repository linked to this paper: 0 ran · 1 unverified.

By repository: 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.

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

libuyu/GHM_Detection officialmentioned in papermentioned on GitHubpytorchMITSyntology: not harvested report
ForrestPi/GHM_Loss mentioned on GitHubtfSyntology: not harvested report
GXYM/GHM_Loss mentioned on GitHubtfSyntology: not harvested report
JennyVanessa/Paddle-GHM mentioned on GitHubpaddleSyntology: not harvested report
peteryuX/tensorflow-GHM-loss mentioned on GitHubtfMITSyntology: 1 sample, 0 ran · 1 unverified report
thisisi3/Paddle-GHM mentioned on GitHubpaddleSyntology: not harvested report
tsdlrh/GHM_paddle mentioned on GitHubpaddleSyntology: not harvested report
xialuxi/GHMLoss-caffe mentioned on GitHubSyntology: not harvested report
open-mmlab/mmdetection pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to An Open and Comprehensive Pipeline for Unified Object Grounding and Detection (arXiv:2401.02361; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 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

1 sample harvested: 0 ran · 1 unverified. 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.

1unverified

Licence: 0 of the 1 sample 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 peteryuX/tensorflow-GHM-loss. “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. “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.

peteryuX/tensorflow-GHM-loss community (archive-listed) 1 sample, 0 ran · 1 unverified
get_ghm_weight tf_ghm_loss.py unverified MIT (permissive) · 82c7307b9b20ffee · report

Tasks

General ClassificationObject DetectionPhilosophy

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO minival GHM-C + GHM-R (RetinaNet-FPN-ResNet-50, M=30) AP50 55.5 #207 of 220 Archive leaderboard report
Object Detection COCO minival GHM-C + GHM-R (RetinaNet-FPN-ResNet-50, M=30) AP75 38.1 #207 of 220 Archive leaderboard report
Object Detection COCO minival GHM-C + GHM-R (RetinaNet-FPN-ResNet-50, M=30) APL 46.7 #207 of 220 Archive leaderboard report
Object Detection COCO minival GHM-C + GHM-R (RetinaNet-FPN-ResNet-50, M=30) APM 39.6 #207 of 220 Archive leaderboard report
Object Detection COCO minival GHM-C + GHM-R (RetinaNet-FPN-ResNet-50, M=30) APS 19.6 #207 of 220 Archive leaderboard report
Object Detection COCO minival GHM-C + GHM-R (RetinaNet-FPN-ResNet-50, M=30) box AP 35.8 #207 of 220 Archive leaderboard report
Object Detection COCO test-dev GHM-C + GHM-R (RetinaNet-FPN-ResNeXt-101) AP50 62.8 #181 of 225 Archive leaderboard report
Object Detection COCO test-dev GHM-C + GHM-R (RetinaNet-FPN-ResNeXt-101) AP75 44.2 #181 of 225 Archive leaderboard report
Object Detection COCO test-dev GHM-C + GHM-R (RetinaNet-FPN-ResNeXt-101) APL 55.3 #181 of 225 Archive leaderboard report
Object Detection COCO test-dev GHM-C + GHM-R (RetinaNet-FPN-ResNeXt-101) APM 45.1 #181 of 225 Archive leaderboard report
Object Detection COCO test-dev GHM-C + GHM-R (RetinaNet-FPN-ResNeXt-101) APS 22.3 #181 of 225 Archive leaderboard report
Object Detection COCO test-dev GHM-C + GHM-R (RetinaNet-FPN-ResNeXt-101) box mAP 41.6 #181 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: GHM-C, GHM-R

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionFocal LossGHM-CGHM-RGlobal Average PoolingGrouped ConvolutionKaiming InitializationMax PoolingReLUResNeXtResNeXt BlockResidual BlockResidual Connection

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