Papers › Feature Pyramid Networks for Object Detection

Feature Pyramid Networks for Object Detection

9 Dec 2016CVPR 2017 7arXiv:1612.03144archive 2025-07-28

Tsung-Yi Lin, Piotr Dollár, Ross Girshick, Kaiming He, Bharath Hariharan, Serge Belongie

Feature pyramids are a basic component in recognition systems for detecting objects at different scales. But recent deep learning object detectors have avoided pyramid representations, in part because they are compute and memory intensive. In this paper, we exploit the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost. A top-down architecture with lateral connections is developed for building high-level semantic feature maps at all scales. This architecture, called a Feature Pyramid Network (FPN), shows significant improvement as a generic feature extractor in several applications. Using FPN in a basic Faster R-CNN system, our method achieves state-of-the-art single-model results on the COCO detection benchmark without bells and whistles, surpassing all existing single-model entries including those from the COCO 2016 challenge winners. In addition, our method can run at 5 FPS on a GPU and thus is a practical and accurate solution to multi-scale object detection. Code will be made publicly available.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 51 code samples harvested from 15 repositories linked to this paper: 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. Where Syntology's instrument failed: 2 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 51 samples from 15 repositories, 33 ran (28 with no instrument failure; 5 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 18 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

85 repositories listed; official and paper-mentioned ones first.

1512159/tf-faster-rcnn-medico mentioned on GitHubtfSyntology: not harvested report
AlphaJia/tf-faster-rcnn mentioned on GitHubtfSyntology: not harvested report
Angzz/fpn-gluon-cv mentioned on GitHubmxnetApache-2.0Syntology: not harvested report
Awia00/Predicted-Path-Tracing mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
CVUsers/Smart-Retail-By-Efficientdet mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
ChestnutLi/tf-faster-rcnn mentioned on GitHubtfSyntology: not harvested report
DetectionTeamUCAS/FPN_Tensorflow mentioned on GitHubtfMITSyntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified report
EMI-Group/FaPN mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
EmGarr/kerod mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
Hernandope/keras_resnet_FPN_cifar10 mentioned on GitHubtfSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
JaryHuang/awesome_SSD_FPN_GIoU mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (1 instrument-failed) · 1 unverified report
Jonydom/Faster-RCNN mentioned on GitHubmindsporeSyntology: not harvested report
Kenneth-Wong/tf-faster-rcnn mentioned on GitHubtfSyntology: not harvested report
KyeongmoonKim/sb mentioned on GitHubtfSyntology: not harvested report
Masao-Taketani/FOTS_OCR mentioned on GitHubtfSyntology: not harvested report
NVIDIA/retinanet-examples mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
Oussamayousre/Yoga_pose_recognizer mentioned on GitHubtfSyntology: not harvested report
PengchengAi/tf-faster-rcnn-pcai mentioned on GitHubtfSyntology: not harvested report
PythonZhengbinChen/tf-faster-rcnn-cpu mentioned on GitHubtfSyntology: not harvested report
RituYadav92/Radar-RGB-Attentive-Multimodal-Object-Detection mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Mask R-CNN (arXiv:1703.06870; that paper's own run record: 101 ran (of which 3 constructed an object rather than computing a result; 77 with no instrument failure: 2 honoured, 1 violated, 74 with no contract checked; 24 where Syntology's instrument failed) · 39 unverified); nothing checks that they implement this paper's method. report
ShihuaHuang95/FaPN-full mentioned on GitHubpytorchSyntology: not harvested report
YudeWang/UNet-Satellite-Image-Segmentation mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to U-Net: Convolutional Networks for Biomedical Image Segmentation (arXiv:1505.04597; that paper's own run record: 530 ran (of which 247 constructed an object rather than computing a result; 378 with no instrument failure: 18 honoured, 10 violated, 350 with no contract checked; 152 where Syntology's instrument failed) · 227 unverified) and Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified); nothing checks that they implement this paper's method. report
achiyaj/vqa-sandbox mentioned on GitHubtfSyntology: not harvested report
adityaarun1/pytorch_fast-er_rcnn mentioned on GitHubpytorchMITSyntology: 8 samples, 7 ran (3 instrument-failed) · 1 unverified report
amritasaha1812/pytorch-faster-rcnn mentioned on GitHubpytorchMITSyntology: 2 samples, 0 ran · 2 unverified report
bareblackfoot/faster-rcnn.selection mentioned on GitHubtfSyntology: not harvested report
bareblackfoot/lddp-tf-faster-rcnn mentioned on GitHubtfSyntology: not harvested report
benihime91/pytorch_retinanet mentioned on GitHubpytorchSyntology: not harvested report
buaaYYC/faster-rcnn-tensorflow mentioned on GitHubtfSyntology: not harvested report
chengzhengxin/groupsoftmax-simpledet mentioned on GitHubmxnetApache-2.0Syntology: not harvested report
chenwuperth/ClaRAN mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Mask R-CNN (arXiv:1703.06870; that paper's own run record: 101 ran (of which 3 constructed an object rather than computing a result; 77 with no instrument failure: 2 honoured, 1 violated, 74 with no contract checked; 24 where Syntology's instrument failed) · 39 unverified); nothing checks that they implement this paper's method. report
cj-mclaughlin/segmentation_research mentioned on GitHubtfSyntology: not harvested report
csmiler/tf-faster-rcnn-cpu mentioned on GitHubtfSyntology: not harvested report
daxiapazi/faster-rcnn mentioned on GitHubtfSyntology: not harvested report
endernewton/tf-faster-rcnn mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Cross-Domain Object Detection Using Unsupervised Image Translation (arXiv:2601.11779; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
facebookresearch/detectron mentioned on GitHubpytorchSyntology: 3 samples, 0 ran · 3 unverified report
guilherme-pombo/keras_resnext_fpn mentioned on GitHubSyntology: not harvested report
hj963434688/Faster_rcnn mentioned on GitHubtfSyntology: not harvested report
huan123/py-fatser-rcnn mentioned on GitHubtfSyntology: not harvested report
insigh/Faster-RCNN-Tensorflow mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (arXiv:1506.01497; that paper's own run record: 79 ran (of which 9 constructed an object rather than computing a result; 47 with no instrument failure: 18 honoured, 5 violated, 24 with no contract checked; 32 where Syntology's instrument failed) · 45 unverified); nothing checks that they implement this paper's method. report
ithuanhuan/gpu-py3-faster-rcnn mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (arXiv:1506.01497; that paper's own run record: 79 ran (of which 9 constructed an object rather than computing a result; 47 with no instrument failure: 18 honoured, 5 violated, 24 with no contract checked; 32 where Syntology's instrument failed) · 45 unverified); nothing checks that they implement this paper's method. report
ithuanhuan/py-fatser-rcnn mentioned on GitHubtfSyntology: not harvested report
jiajunhua/facebookresearch-Detectron mentioned on GitHubcaffe2Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (arXiv:1506.01497; that paper's own run record: 79 ran (of which 9 constructed an object rather than computing a result; 47 with no instrument failure: 18 honoured, 5 violated, 24 with no contract checked; 32 where Syntology's instrument failed) · 45 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Aggregated Residual Transformations for Deep Neural Networks (arXiv:1611.05431; that paper's own run record: 51 ran (of which 7 constructed an object rather than computing a result; 31 with no instrument failure: 0 honoured, 0 violated, 31 with no contract checked; 20 where Syntology's instrument failed) · 29 unverified) and 2 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
jndeng/DACSDC-DeepZ mentioned on GitHubSyntology: not harvested report
kuangliu/pytorch-fpn mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
libiseller/MobileNetV2-dynamicFPN mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
liuqiang3/faster_rcnn mentioned on GitHubtfSyntology: not harvested report
mengyingfei/faster-rcnn-tf mentioned on GitHubtfSyntology: not harvested report
nautilus261/tf-faster-rcnn mentioned on GitHubtfSyntology: not harvested report
neuqgz/modify-faster-rcnn-tf mentioned on GitHubtfSyntology: not harvested report
pawelbeza/ClothesDetectorModel mentioned on GitHubpytorchSyntology: not harvested report
piaosonglin1985/tf-faster-rcnn mentioned on GitHubtfSyntology: not harvested report
pratikshaya/image-data-augmentation-for-object-detection mentioned on GitHubSyntology: not harvested report
r06942054/NOTE-RCNN mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (arXiv:1506.01497; that paper's own run record: 79 ran (of which 9 constructed an object rather than computing a result; 47 with no instrument failure: 18 honoured, 5 violated, 24 with no contract checked; 32 where Syntology's instrument failed) · 45 unverified); nothing checks that they implement this paper's method. report
raphael-cohen/capsnet_for_Faster-RCNN mentioned on GitHubpytorchMITSyntology: not harvested report
rickyHong/FPN-repl mentioned on GitHubSyntology: not harvested report
rickyHong/faster-rcnn-tensorflow-repl mentioned on GitHubtfSyntology: not harvested report
rickyHong/pytorch-faster-rcnn-repl mentioned on GitHubpytorchMITSyntology: not harvested report
ruotianluo/pytorch-faster-rcnn mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (arXiv:1506.01497; that paper's own run record: 79 ran (of which 9 constructed an object rather than computing a result; 47 with no instrument failure: 18 honoured, 5 violated, 24 with no contract checked; 32 where Syntology's instrument failed) · 45 unverified); nothing checks that they implement this paper's method. report
shikorab/tf-faster-rcnn mentioned on GitHubtfSyntology: not harvested report
shun601/4th-tellus-satellite-challenge mentioned on GitHubpytorchSyntology: not harvested report
soeaver/py-RFCN-priv mentioned on GitHubMITSyntology: 8 samples, 6 ran (0 instrument-failed) · 2 unverified report
sonnguyen64/horus-tf-faster-rcnn mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (arXiv:1506.01497; that paper's own run record: 79 ran (of which 9 constructed an object rather than computing a result; 47 with no instrument failure: 18 honoured, 5 violated, 24 with no contract checked; 32 where Syntology's instrument failed) · 45 unverified); nothing checks that they implement this paper's method. report
tensorpack/tensorpack mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Playing Atari with Deep Reinforcement Learning (arXiv:1312.5602; that paper's own run record: 64 ran (of which 24 constructed an object rather than computing a result; 46 with no instrument failure: 5 honoured, 0 violated, 41 with no contract checked; 18 where Syntology's instrument failed) · 53 unverified), Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks (arXiv:1511.06434; that paper's own run record: 128 ran (of which 61 constructed an object rather than computing a result; 111 with no instrument failure: 3 honoured, 0 violated, 108 with no contract checked; 17 where Syntology's instrument failed) · 91 unverified) and Improved Training of Wasserstein GANs (arXiv:1704.00028; that paper's own run record: 27 ran (of which 10 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 0 violated, 18 with no contract checked; 8 where Syntology's instrument failed) · 22 unverified); nothing checks that they implement this paper's method. report
tianhai123/tf-faster-rcnn mentioned on GitHubtfSyntology: not harvested report
tigerofmurder/tf-faster-rcnn mentioned on GitHubtfSyntology: not harvested report
tusimple/simpledet mentioned on GitHubmxnetApache-2.0Syntology: not harvested report
unsky/FPN mentioned on GitHubSyntology: not harvested report
vietlinhtspt/NewFasterRCNN mentioned on GitHubtfSyntology: not harvested report
wangzpeng/tf-faster-rcnn mentioned on GitHubtfSyntology: not harvested report
wennieWN/endernewton_tf-faster-rcnn mentioned on GitHubtfSyntology: not harvested report
xinpingwang/tf-faster-rcnn mentioned on GitHubtfSyntology: not harvested report
yanxp/rcnn-discovery mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (arXiv:1506.01497; that paper's own run record: 79 ran (of which 9 constructed an object rather than computing a result; 47 with no instrument failure: 18 honoured, 5 violated, 24 with no contract checked; 32 where Syntology's instrument failed) · 45 unverified); nothing checks that they implement this paper's method. report
yfnn/fused-model mentioned on GitHubtfMITSyntology: 7 samples, 4 ran (1 instrument-failed) · 3 unverified report
yfnn/person_subclass mentioned on GitHubtfSyntology: not harvested report
yzgrfsy/tf-fastrcnn-crop mentioned on GitHubtfSyntology: not harvested report
zhongzisha/object_detection mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FCOS: Fully Convolutional One-Stage Object Detection (arXiv:1904.01355; that paper's own run record: 37 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 2 honoured, 2 violated, 26 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
zxqcreations/faster-rcnn-tf mentioned on GitHubtfSyntology: not harvested report
MindSpore-scientific/code-2 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets (arXiv:2311.15127; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. 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
PaddlePaddle/PaddleOCR paddleApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to KRETA: A Benchmark for Korean Reading and Reasoning in Text-Rich VQA Attuned to... (arXiv:2508.19944; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
addisonklinke/pytorch-architectures pytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified 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
yangyucheng000/Paper-3 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DPSUR: Accelerating Differentially Private Stochastic Gradient Descent Using Selective... (arXiv:2311.14056; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 7 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

51 samples harvested: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · honoured contract
2ran · our draft was wrong
3ran; the contract check could not run
24ran
18unverified

Licence: 11 of the 51 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 15 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”. For 5 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

Awia00/Predicted-Path-Tracing community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
PyramidNet predicter/src/ml_models/conv_model.py ran MIT (permissive) · ea9064c0a898ac01 · report fixture: returned PyramidNet · level recorded 2026-09-22
CVUsers/Smart-Retail-By-Efficientdet community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
Conv2dStaticSamePadding in 5 papers efficientdet/model.py ran fingerprinted LGPL-3.0 (copyleft) · pointer only · 772be90118bbbd9d · report fixture: returned Conv2dStaticSamePadding · level recorded 2026-09-22
MaxPool2dStaticSamePadding efficientdet/model.py ran fingerprinted LGPL-3.0 (copyleft) · pointer only · 339edf626eec5843 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
MemoryEfficientSwish efficientdet/model.py ran fingerprinted LGPL-3.0 (copyleft) · pointer only · fa6edb4bad3d19cf · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
SeparableConvBlock efficientdet/model.py ran fingerprinted LGPL-3.0 (copyleft) · pointer only · a1707ef37ec1150a · report fixture: returned SeparableConvBlock · level recorded 2026-09-22
BiFPN efficientdet/model.py unverified LGPL-3.0 (copyleft) · pointer only · 69419cc979788b48 · report
DetectionTeamUCAS/FPN_Tensorflow community (archive-listed) 4 samples, 2 ran (0 instrument-failed) · 2 unverified
enum_ratios libs/box_utils/anchor_utils.py ran MIT (permissive) · d8ac71fa434ec2ea · report fixture: signature anchors:EagerTensor/2/float, anchor_ratios:list/1/float · returned tuple · level recorded 2026-09-26
enum_scales libs/box_utils/anchor_utils.py ran MIT (permissive) · d7d04d0980025fa0 · report fixture: signature base_anchor:EagerTensor/1/float, anchor_scales:list/1/float · returned SymbolicTensor · level recorded 2026-09-24
smooth_l1_loss_rcnn libs/losses/losses.py unverified MIT (permissive) · 3d022f5cf8c2caf2 · report
smooth_l1_loss_rpn libs/losses/losses.py unverified MIT (permissive) · ca0e5a26e6b42e13 · report
EmGarr/kerod community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
FPN in 5 papers src/kerod/model/backbone/fpn.py ran MIT (permissive) · c1805312215d9d89 · report fixture: signature inputs:list/1/EagerTensor · returned list · level recorded 2026-09-24
Hernandope/keras_resnet_FPN_cifar10 community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
customFeaturePyramid2 new_model.py ran no licence file found · pointer only · 449d4ad43176a0be · report fixture: returned customFeaturePyramid2 · level recorded 2026-09-22
get_backbone_ResNet50 new_model.py unverified no licence file found · pointer only · 7fed2f2ab4f55b42 · report
JaryHuang/awesome_SSD_FPN_GIoU community (archive-listed) 3 samples, 2 ran (1 instrument-failed) · 1 unverified
ConvModule in 8 papers model/neck/build_neck.py ran fingerprinted no licence file found · pointer only · b05c3c290ce6a7be · report fixture: signature x:Tensor/4/float, activate:bool/0/bool, norm:bool/0/bool · returned Tensor · level recorded 2026-09-24
build_norm_layer in 14 papers model/neck/build_neck.py ran · our draft was wrong no licence file found · pointer only · 716379f26990238c · report fixture: signature cfg:dict/0/?, num_features:int/0/int, postfix:str/0/str · returned tuple · level recorded 2026-09-22
Neck model/neck/build_neck.py unverified no licence file found · pointer only · b758bf3a1b1211b9 · report
NVIDIA/retinanet-examples community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
MobileNet in 6 papers odtk/backbones/fpn.py ran fingerprinted BSD-3-Clause (permissive) · 3090c14f8b34c8a7 · report fixture: returned MobileNet · level recorded 2026-09-22
ResNet in 139 papers odtk/backbones/fpn.py ran fingerprinted BSD-3-Clause (permissive) · 921caec48084ca6e · report fixture: returned ResNet · level recorded 2026-09-22
FPN in 5 papers odtk/backbones/fpn.py unverified BSD-3-Clause (permissive) · 28fc17a368114e36 · report
adityaarun1/pytorch_fast-er_rcnn community (archive-listed) 8 samples, 7 ran (3 instrument-failed) · 1 unverified
generate_anchors in 19 papers lib/layer_utils/generate_anchors.py ran; the contract check could not run (RAISES) MIT (permissive) · d4f2ade15edff997 · report fixture: signature base_size:int/0/int, ratios:list/1/float, scales:ndarray/1/int · returned ndarray · level recorded 2026-09-26
parse_rec in 26 papers lib/datasets/voc_eval.py ran · our draft was wrong MIT (permissive) · 0eafc51289a49033 · report fixture: signature filename:str/0/str · returned list · level recorded 2026-09-26
unique_boxes in 21 papers lib/datasets/ds_utils.py ran · honoured contract fingerprinted MIT (permissive) · 8a015c012f507631 · report fixture: signature boxes:ndarray/2/float, scale:float/0/float · returned ndarray · level recorded 2026-09-26
voc_ap in 44 papers
census: 5 implementations from 10 papers, 2 distinct outputs on one shared input
lib/datasets/voc_eval.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · ec3e5aa793d6ce69 · report fixture: signature rec:ndarray/1/float, prec:ndarray/1/float, use_07_metric:bool/0/bool · returned float64 · level recorded 2026-09-26
voc_eval in 19 papers lib/datasets/voc_eval.py ran MIT (permissive) · 827e4bc3c7da80ac · report fixture: signature detpath:str/0/str, annopath:str/0/str, imagesetfile:str/0/str, classname:str/0/str, cachedir:str/0/str, ovthresh:float/0/float, use_07_metric:bool/0/bool, use_diff:bool/0/bool · returned tuple · level recorded 2026-09-26
xywh_to_xyxy in 24 papers lib/datasets/ds_utils.py ran · honoured contract fingerprinted MIT (permissive) · d3e019b11b709edb · report fixture: signature boxes:ndarray/2/float · returned ndarray · level recorded 2026-09-26
xyxy_to_xywh in 23 papers lib/datasets/ds_utils.py ran · honoured contract fingerprinted MIT (permissive) · a832e5017f504280 · report fixture: signature boxes:ndarray/2/float · returned ndarray · level recorded 2026-09-26
get_imdb in 22 papers lib/datasets/factory.py unverified MIT (permissive) · 3be9228820b46ef3 · report
amritasaha1812/pytorch-faster-rcnn community (archive-listed) 2 samples, 0 ran · 2 unverified
parse_rec in 26 papers lib/datasets/vg_eval.py unverified MIT (permissive) · accdc6767e6b33bc · report
vg_eval lib/datasets/vg_eval.py unverified MIT (permissive) · ab4052621f3a25ba · report
facebookresearch/detectron community (archive-listed) 3 samples, 0 ran · 3 unverified
add_fpn detectron/modeling/FPN.py unverified Apache-2.0 (permissive) · 35e467326215e55a · report
add_topdown_lateral_module detectron/modeling/FPN.py unverified Apache-2.0 (permissive) · 3530b0d7b0948c75 · report
get_min_max_levels detectron/modeling/FPN.py unverified Apache-2.0 (permissive) · 42feb79923ca7dc9 · report
kuangliu/pytorch-fpn community (archive-listed) 1 sample, 0 ran · 1 unverified
FPN in 5 papers fpn.py unverified no licence file found · pointer only · d25d1d3ee749a68f · report
libiseller/MobileNetV2-dynamicFPN community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
InvertedResidual in 9 papers MobileNetV2_dynamicFPN.py ran MIT (permissive) · 3bbf9937427a6a38 · report fixture: returned InvertedResidual · level recorded 2026-09-22
MobileNetV2_dynamicFPN MobileNetV2_dynamicFPN.py ran fingerprinted MIT (permissive) · cab0da568d0255ff · report fixture: returned MobileNetV2_dynamicFPN · level recorded 2026-09-22
soeaver/py-RFCN-priv community (archive-listed) 8 samples, 6 ran (0 instrument-failed) · 2 unverified
blobproto_to_array in 5 papers caffe-priv/python/caffe/io.py ran MIT (permissive) · 093b959c347fd2f5 · report fixture: signature blob:BlobProto/0/?, return_diff:bool/0/bool · returned ndarray · level recorded 2026-09-25
choose_color_by_layertype in 5 papers caffe-priv/python/caffe/draw.py ran fingerprinted MIT (permissive) · a847938e3819a686 · report fixture: signature layertype:str/0/str · returned str · level recorded 2026-09-25
conv_params in 5 papers caffe-priv/python/caffe/coord_map.py ran MIT (permissive) · fc3a459b0c468f41 · report fixture: signature fn:MockFn/0/? · returned tuple · level recorded 2026-09-25
coord_map caffe-priv/python/caffe/coord_map.py ran MIT (permissive) · c85f4a53630aa36a · report fixture: signature fn:MockLayer/0/? · returned tuple · level recorded 2026-09-25
crop_params caffe-priv/python/caffe/coord_map.py ran MIT (permissive) · e8a3c25030f4c88c · report fixture: signature fn:MockFunction/0/? · returned tuple · level recorded 2026-09-25
get_edge_label in 5 papers caffe-priv/python/caffe/draw.py ran MIT (permissive) · 2876e38623f7acbc · report fixture: signature layer:Layer/0/? · returned str · level recorded 2026-09-25
array_to_blobproto in 5 papers caffe-priv/python/caffe/io.py unverified MIT (permissive) · 61cfa43a945cbe3b · report
arraylist_to_blobprotovector_str caffe-priv/python/caffe/io.py unverified MIT (permissive) · 6b3d943a10eb2014 · report
yfnn/fused-model community (archive-listed) 7 samples, 4 ran (1 instrument-failed) · 3 unverified
bbox_transform in 11 papers lib/model/bbox_transform.py ran fingerprinted MIT (permissive) · d4fe87e32593516b · report fixture: signature ex_rois:ndarray/2/float, gt_rois:ndarray/2/float · returned ndarray · level recorded 2026-09-26
bbox_transform_inv in 11 papers lib/model/bbox_transform.py ran · honoured contract fingerprinted MIT (permissive) · b3695ebe0c382b05 · report fixture: signature boxes:ndarray/2/float, deltas:ndarray/2/float · returned ndarray · level recorded 2026-09-22
clip_boxes in 10 papers lib/model/bbox_transform.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 6c939ab027a6b144 · report fixture: signature boxes:ndarray/2/float, im_shape:tuple/1/int · returned ndarray · level recorded 2026-09-22
parse_rec in 26 papers lib/datasets/voc_eval.py ran MIT (permissive) · 4da53b2d2f55c949 · report fixture: signature filename:str/0/str · returned list · level recorded 2026-09-26
get_output_dir in 18 papers lib/model/config.py unverified MIT (permissive) · d2840813f8bef8d7 · report
get_output_tb_dir lib/model/config.py unverified MIT (permissive) · b4096d8dc1f6bcc3 · report
voc_eval in 19 papers lib/datasets/voc_eval.py unverified MIT (permissive) · ab2edac69f63b46a · report
addisonklinke/pytorch-architectures community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
FeaturePyramid torcharch/conv.py ran · metamorphic tier: deterministic MIT (permissive) · a4ac0f94315a1301 · report fixture: returned FeaturePyramid · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

10 assemblies on this paper: 10 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

10 sibling assemblies for Feature Pyramid Network (FPN) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Feature Pyramid Network (FPN) (graph method: Feature Pyramid Network (FPN)). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 10 siblings

  1. FeaturePyramid entry · level 1 · ran · a4ac0f94315a1301

harvested Assembly for Feature Pyramid Network (FPN) (graph method: Feature Pyramid Network (FPN)). 2 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 10 siblings

  1. customFeaturePyramid2 entry · level 1 · ran · 449d4ad43176a0be
  2. get_backbone_ResNet50 model · level 0 · unverified · 7fed2f2ab4f55b42

harvested Assembly for Feature Pyramid Network (FPN) (graph method: Feature Pyramid Network (FPN)). 7 bricks; individually on a fixture: 6 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 10 siblings

  1. BiFPN entry · level 0 · unverified · 69419cc979788b48
  2. Conv2dStaticSamePadding helper · level 1 · ran · 772be90118bbbd9d
  3. MaxPool2dStaticSamePadding helper · level 1 · ran · 339edf626eec5843
  4. MemoryEfficientSwish helper · level 1 · ran · fa6edb4bad3d19cf
  5. SeparableConvBlock helper · level 1 · ran · a1707ef37ec1150a
  6. Swish helper · level 1 · ran · 1b5e656b7306390c
  7. SwishImplementation helper · level 1 · ran · 6fca2143a077d04e

harvested Assembly for Feature Pyramid Network (FPN) (graph method: Feature Pyramid Network (FPN)). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 10 siblings

  1. FPN entry · level 1 · ran · c1805312215d9d89

harvested Assembly for Feature Pyramid Network (FPN) (graph method: Feature Pyramid Network (FPN)). 3 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 10 siblings

  1. FPN entry · level 0 · unverified · 28fc17a368114e36
  2. MobileNet model · level 1 · ran · 3090c14f8b34c8a7
  3. ResNet model · level 1 · ran · 921caec48084ca6e

harvested Assembly for Feature Pyramid Network (FPN) (graph method: Feature Pyramid Network (FPN)). 6 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

one of 10 siblings

  1. add_fpn entry · level 0 · unverified · 35e467326215e55a
  2. add_topdown_lateral_module model · level 0 · unverified · 3530b0d7b0948c75
  3. const_fill helper · level 1 · ran · our draft was wrong · 93f6fc328f31783a
  4. get_group_gn helper · level 0 · unverified · 8bc93accde20e097
  5. get_min_max_levels helper · level 0 · unverified · 42feb79923ca7dc9
  6. AttrDict helper · level 0 · unverified · 5904b95e70b5177a

harvested Assembly for Feature Pyramid Network (FPN) (graph method: Feature Pyramid Network (FPN)). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 10 siblings

  1. PyramidNet entry · level 1 · ran · ea9064c0a898ac01

harvested Assembly for Feature Pyramid Network (FPN) (graph method: Feature Pyramid Network (FPN)). 2 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 10 siblings

  1. MobileNetV2_dynamicFPN entry · level 1 · ran · cab0da568d0255ff
  2. InvertedResidual model · level 1 · ran · 3bbf9937427a6a38

harvested Assembly for Feature Pyramid Network (FPN) (graph method: Feature Pyramid Network (FPN)). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 10 siblings

  1. FPN entry · level 0 · unverified · d25d1d3ee749a68f

harvested Assembly for Feature Pyramid Network (FPN) (graph method: Feature Pyramid Network (FPN)). 3 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 10 siblings

  1. Neck entry · level 0 · unverified · b758bf3a1b1211b9
  2. ConvModule helper · level 1 · ran · b05c3c290ce6a7be
  3. build_norm_layer helper · level 1 · ran · our draft was wrong · 716379f26990238c

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1612.03144") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

ObjectObject DetectionPedestrian DetectionSemantic Segmentation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO minival FPN+ AP50 61.3 #185 of 220 Archive leaderboard report
Object Detection COCO minival FPN+ AP75 43.3 #185 of 220 Archive leaderboard report
Object Detection COCO minival FPN+ APL 52.6 #185 of 220 Archive leaderboard report
Object Detection COCO minival FPN+ APM 43.3 #185 of 220 Archive leaderboard report
Object Detection COCO minival FPN+ APS 22.9 #185 of 220 Archive leaderboard report
Object Detection COCO minival FPN+ box AP 39.8 #185 of 220 Archive leaderboard report
Object Detection COCO test-dev Faster R-CNN + FPN Hardware Burden 2G #224 of 225 Archive leaderboard report
Object Detection COCO test-dev Faster R-CNN + FPN box mAP 36.2 #224 of 225 Archive leaderboard report
Pedestrian Detection TJU-Ped-traffic FPN ALL (miss rate) 37.78 #4 of 6 Archive leaderboard report
Pedestrian Detection TJU-Ped-traffic FPN HO (miss rate) 60.30 #4 of 6 Archive leaderboard report
Pedestrian Detection TJU-Ped-traffic FPN R (miss rate) 22.30 #4 of 6 Archive leaderboard report
Pedestrian Detection TJU-Ped-traffic FPN R+HO (miss rate) 26.71 #4 of 6 Archive leaderboard report
Pedestrian Detection TJU-Ped-traffic FPN RS (miss rate) 35.19 #4 of 6 Archive leaderboard report
Semantic Segmentation Potsdam FPN mIoU 82.99 #10 of 11 Archive leaderboard report
Semantic Segmentation US3D FPN mIoU 72.51 #10 of 11 Archive leaderboard report
Semantic Segmentation Vaihingen FPN mIoU 74.86 #12 of 13 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

1x1 ConvolutionConvolutionFPNFaster R-CNNRPNRoIPoolSoftmax

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