Papers › M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network

M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network

12 Nov 2018arXiv:1811.04533archive 2025-07-28

Qijie Zhao, Tao Sheng, Yongtao Wang, Zhi Tang, Ying Chen, Ling Cai, Haibin Ling

Feature pyramids are widely exploited by both the state-of-the-art one-stage object detectors (e.g., DSSD, RetinaNet, RefineDet) and the two-stage object detectors (e.g., Mask R-CNN, DetNet) to alleviate the problem arising from scale variation across object instances. Although these object detectors with feature pyramids achieve encouraging results, they have some limitations due to that they only simply construct the feature pyramid according to the inherent multi-scale, pyramidal architecture of the backbones which are actually designed for object classification task. Newly, in this work, we present a method called Multi-Level Feature Pyramid Network (MLFPN) to construct more effective feature pyramids for detecting objects of different scales. First, we fuse multi-level features (i.e. multiple layers) extracted by backbone as the base feature. Second, we feed the base feature into a block of alternating joint Thinned U-shape Modules and Feature Fusion Modules and exploit the decoder layers of each u-shape module as the features for detecting objects. Finally, we gather up the decoder layers with equivalent scales (sizes) to develop a feature pyramid for object detection, in which every feature map consists of the layers (features) from multiple levels. To evaluate the effectiveness of the proposed MLFPN, we design and train a powerful end-to-end one-stage object detector we call M2Det by integrating it into the architecture of SSD, which gets better detection performance than state-of-the-art one-stage detectors. Specifically, on MS-COCO benchmark, M2Det achieves AP of 41.0 at speed of 11.8 FPS with single-scale inference strategy and AP of 44.2 with multi-scale inference strategy, which is the new state-of-the-art results among one-stage detectors. The code will be made available on https://github.com/qijiezhao/M2Det.

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 1 code sample harvested from 1 repository 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) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 1 sample from 1 repository, 1 ran (1 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

CVUsers/Smart-Retail-By-Efficientdet mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Feature Pyramid Networks for Object Detection (arXiv:1612.03144; that paper's own run record: 33 ran (of which 9 constructed an object rather than computing a result; 28 with no instrument failure: 4 honoured, 0 violated, 24 with no contract checked; 5 where Syntology's instrument failed) · 18 unverified); nothing checks that they implement this paper's method. report
LeeDongYeun/keras-m2det mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
cjpurackal/m2det-tf mentioned on GitHubtfSyntology: not harvested report
taashi-s/M2Det_keras mentioned on GitHubSyntology: not harvested report
true-source/m2det-tf mentioned on GitHubtfSyntology: not harvested report
2023-MindSpore-1/ms-code-18 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code-5 mindsporeSyntology: not harvested report
Mind23-2/MindCode-101 mindsporeSyntology: not harvested report
Mind23-2/MindCode-3 mindsporeSyntology: not harvested report
code-implementation1/Code5 mindsporeSyntology: not harvested report
xiuyu0000/new_papers_codes mindsporeSyntology: not harvested 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: 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) · 0 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

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 LeeDongYeun/keras-m2det. “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.

LeeDongYeun/keras-m2det community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
upsample_add_output_shape keras_m2det/models/m2det.py ran · honoured contract Apache-2.0 (permissive) · 87e732b8bf7dbe08 · report fixture: signature input_shapes:list/1/tuple · returned list · level recorded 2026-09-22

Tasks

DecoderObjectObject Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO minival M2Det (ResNet-1o1, 320x320) AP50 53.7 #209 of 220 Archive leaderboard report
Object Detection COCO minival M2Det (ResNet-1o1, 320x320) APL 49.3 #209 of 220 Archive leaderboard report
Object Detection COCO minival M2Det (ResNet-1o1, 320x320) APM 39.5 #209 of 220 Archive leaderboard report
Object Detection COCO minival M2Det (ResNet-1o1, 320x320) APS 15.9 #209 of 220 Archive leaderboard report
Object Detection COCO minival M2Det (ResNet-1o1, 320x320) box AP 34.1 #209 of 220 Archive leaderboard report
Object Detection COCO minival M2Det (VGG-16, 320x320) AP50 52.2 #211 of 220 Archive leaderboard report
Object Detection COCO minival M2Det (VGG-16, 320x320) APL 49.1 #211 of 220 Archive leaderboard report
Object Detection COCO minival M2Det (VGG-16, 320x320) APM 38.2 #211 of 220 Archive leaderboard report
Object Detection COCO minival M2Det (VGG-16, 320x320) APS 15 #211 of 220 Archive leaderboard report
Object Detection COCO minival M2Det (VGG-16, 320x320) box AP 33.2 #211 of 220 Archive leaderboard report
Object Detection COCO test-dev M2Det (VGG-16, multi-scale) AP50 64.6 #150 of 225 Archive leaderboard report
Object Detection COCO test-dev M2Det (VGG-16, multi-scale) AP75 49.3 #150 of 225 Archive leaderboard report
Object Detection COCO test-dev M2Det (VGG-16, multi-scale) APL 55.1 #150 of 225 Archive leaderboard report
Object Detection COCO test-dev M2Det (VGG-16, multi-scale) APM 47.9 #150 of 225 Archive leaderboard report
Object Detection COCO test-dev M2Det (VGG-16, multi-scale) APS 29.2 #150 of 225 Archive leaderboard report
Object Detection COCO test-dev M2Det (VGG-16, multi-scale) Hardware Burden 34G #150 of 225 Archive leaderboard report
Object Detection COCO test-dev M2Det (VGG-16, multi-scale) box mAP 44.2 #150 of 225 Archive leaderboard report
Object Detection COCO test-dev M2Det (ResNet-101, multi-scale) AP50 64.4 #152 of 225 Archive leaderboard report
Object Detection COCO test-dev M2Det (ResNet-101, multi-scale) AP75 48 #152 of 225 Archive leaderboard report
Object Detection COCO test-dev M2Det (ResNet-101, multi-scale) APL 54.3 #152 of 225 Archive leaderboard report
Object Detection COCO test-dev M2Det (ResNet-101, multi-scale) APM 49.6 #152 of 225 Archive leaderboard report
Object Detection COCO test-dev M2Det (ResNet-101, multi-scale) APS 29.6 #152 of 225 Archive leaderboard report
Object Detection COCO test-dev M2Det (ResNet-101, multi-scale) Hardware Burden 27G #152 of 225 Archive leaderboard report
Object Detection COCO test-dev M2Det (ResNet-101, multi-scale) box mAP 43.9 #152 of 225 Archive leaderboard report
Object Detection COCO test-dev M2Det (VGG-16, single-scale) AP50 59.7 #185 of 225 Archive leaderboard report
Object Detection COCO test-dev M2Det (VGG-16, single-scale) AP75 45 #185 of 225 Archive leaderboard report
Object Detection COCO test-dev M2Det (VGG-16, single-scale) APL 53.8 #185 of 225 Archive leaderboard report
Object Detection COCO test-dev M2Det (VGG-16, single-scale) APM 46.5 #185 of 225 Archive leaderboard report
Object Detection COCO test-dev M2Det (VGG-16, single-scale) APS 22.1 #185 of 225 Archive leaderboard report
Object Detection COCO test-dev M2Det (VGG-16, single-scale) Hardware Burden 34G #185 of 225 Archive leaderboard report
Object Detection COCO test-dev M2Det (VGG-16, single-scale) box mAP 41.0 #185 of 225 Archive leaderboard report
Object Detection COCO test-dev M2Det (ResNet-101, single-scale) AP50 59.4 #210 of 225 Archive leaderboard report
Object Detection COCO test-dev M2Det (ResNet-101, single-scale) AP75 41.7 #210 of 225 Archive leaderboard report
Object Detection COCO test-dev M2Det (ResNet-101, single-scale) APL 53.4 #210 of 225 Archive leaderboard report
Object Detection COCO test-dev M2Det (ResNet-101, single-scale) APM 43.9 #210 of 225 Archive leaderboard report
Object Detection COCO test-dev M2Det (ResNet-101, single-scale) APS 20.5 #210 of 225 Archive leaderboard report
Object Detection COCO test-dev M2Det (ResNet-101, single-scale) Hardware Burden 27G #210 of 225 Archive leaderboard report
Object Detection COCO test-dev M2Det (ResNet-101, single-scale) box mAP 38.8 #210 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: FFMv1, FFMv2, M2Det, MLFPN

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionDense ConnectionsDropoutFFMv1FFMv2FPNFocal LossGlobal Average PoolingKaiming InitializationLinear WarmupM2DetMLFPNMask R-CNNMax PoolingNon Maximum SuppressionRPNReLUResidual BlockResidual ConnectionRetinaNetRoIAlignSFAMSGD with MomentumSSDSigmoid ActivationSoftmaxStep DecayTUMWeight Decay

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