Papers › FCOS: Fully Convolutional One-Stage Object Detection

FCOS: Fully Convolutional One-Stage Object Detection

2 Apr 2019ICCV 2019 10arXiv:1904.01355archive 2025-07-28

Zhi Tian, Chunhua Shen, Hao Chen, Tong He

We propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to semantic segmentation. Almost all state-of-the-art object detectors such as RetinaNet, SSD, YOLOv3, and Faster R-CNN rely on pre-defined anchor boxes. In contrast, our proposed detector FCOS is anchor box free, as well as proposal free. By eliminating the predefined set of anchor boxes, FCOS completely avoids the complicated computation related to anchor boxes such as calculating overlapping during training. More importantly, we also avoid all hyper-parameters related to anchor boxes, which are often very sensitive to the final detection performance. With the only post-processing non-maximum suppression (NMS), FCOS with ResNeXt-64x4d-101 achieves 44.7% in AP with single-model and single-scale testing, surpassing previous one-stage detectors with the advantage of being much simpler. For the first time, we demonstrate a much simpler and flexible detection framework achieving improved detection accuracy. We hope that the proposed FCOS framework can serve as a simple and strong alternative for many other instance-level tasks. Code is available at:Code is available at: https://tinyurl.com/FCOSv1

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

The archive's official repository (tianzhi0549/FCOS) was not harvested; the 39 samples below come from 15 community repositories, and 1 more is identical to code Syntology harvested from another paper's repository.

Syntology 40 code samples: 39 from 15 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 40: 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. Where Syntology's instrument failed: 6 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 39 samples from 15 repositories, 36 ran (29 with no instrument failure; 7 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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 9 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. 4 of the 37 samples that ran have no recorded date.

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

tianzhi0549/FCOS officialmentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
yqyao/FCOS_PLUS mentioned in paperpytorchNOASSERTIONSyntology: not harvested report
Adelaide-AI-Group/FCOS mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
BIYTC/mobilenet_maskrcnn mentioned on GitHubpytorchMITSyntology: 4 samples, 4 ran (1 instrument-failed) · 0 unverified report
DetectionTeamUCAS/FCOS_GluonCV mentioned on GitHubmxnetApache-2.0Syntology: not harvested report
FluteXu/ms-project mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
GuoLiuFang/maskrcnn-benchmark-lfs mentioned on GitHubpytorchMITSyntology: not harvested report
HRNet/HRNet-FCOS mentioned on GitHubpytorchSyntology: not harvested report
Iamal1/maskrcnn-benchmark mentioned on GitHubpytorchMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
MalongTech/research-fad mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
Mind23-2/MindCode-46 mentioned on GitHubmindsporeSyntology: not harvested report
Mind23-2/MindCode-47 mentioned on GitHubmindsporeSyntology: not harvested report
Miracle1991/DetectionHub mentioned on GitHubpytorchSyntology: not harvested report
OFRIN/Tensorflow_FCOS mentioned on GitHubtfSyntology: not harvested report
PeterTKovacs/zold137 mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
Pxtri2156/AdelaiDet_v2 mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Conditional Convolutions for Instance Segmentation (arXiv:2003.05664; that paper's own run record: 2 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; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
SilvioGiancola/maskrcnn-benchmark mentioned on GitHubpytorchMITSyntology: not harvested report
Yuxiang1995/ICDAR2021_MFD mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense... (arXiv:2006.04388; that paper's own run record: 22 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; 1 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
Zanderzt/TensorRT_Mask_RCNN mentioned on GitHubpytorchMITSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
ZhZiKai/VisDrone_FCOS mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
Zhang-Jing-Xuan/MaskRCNN mentioned on GitHubpytorchnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report
Zhangyongtao123/maskrcnn_benchmark mentioned on GitHubpytorchMITSyntology: not harvested report
abcxs/maskrcnn-contest mentioned on GitHubpytorchMITSyntology: not harvested report
aim-uofa/AdelaiDet mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
aim-uofa/adet mentioned on GitHubpytorchSyntology: not harvested report
alannguyencs/maskrcnn mentioned on GitHubpytorchMITSyntology: not harvested report
aotumanbiu/awesome-object-detection mentioned on GitHubpytorchSyntology: not harvested report
banben/maskrcnn-benchmark mentioned on GitHubpytorchMITSyntology: not harvested report
basaltzhang/maskrcnn-benchmark mentioned on GitHubpytorchMITSyntology: not harvested report
bimsarapathiraja/mccl mentioned on GitHubpytorchNOASSERTIONSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Multiclass Confidence and Localization Calibration for Object Detection (arXiv:2306.08271; that paper's own run record: 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); nothing checks that they implement this paper's method. report
blueardour/AdelaiDet mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
ccchang1023/maskrcnn-benchmark mentioned on GitHubpytorchMITSyntology: not harvested report
chencq1234/maskrcnn_facebook mentioned on GitHubpytorchMITSyntology: not harvested report
cshizhe/maskrcnn_benchmark mentioned on GitHubpytorchMITSyntology: not harvested report
cyctrung/DPnet mentioned on GitHubpytorchMITSyntology: not harvested report
delmalih/MIAS-mammography-obj-detection mentioned on GitHubpytorchSyntology: not harvested report
fcakyon/sahi-benchmark mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection (arXiv:2202.06934; that paper's own run record: 18 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
feng-lab/nuclei mentioned on GitHubpytorchMITSyntology: not harvested report
jahutwb/DL_dosimetry mentioned on GitHubpytorchMITSyntology: not harvested report
jonvthvn90/Project mentioned on GitHubpytorchMITSyntology: not harvested report
kohillyang/mx-detection mentioned on GitHubmxnetSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
latentgnn/maskrcnn-benchmark-latentgnn mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
lijain/FCOS-change mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
lipengfeizju/Detection mentioned on GitHubpytorchMITSyntology: not harvested report
lipengyuMachineLearner/FCOS mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
lippman1125/maskrcnn_benchmark_mobilenetv2 mentioned on GitHubpytorchMITSyntology: not harvested report
lzrobots/dgmn mentioned on GitHubpytorchMITSyntology: not harvested report
markson14/WheatDet mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
moallafatma/Breast_Cancer_Detection_Classification mentioned on GitHubpytorchSyntology: not harvested report
monk-ai/maskrcnn mentioned on GitHubpytorchMITSyntology: not harvested report
neilctwu/FCOS-pytorch_Simplified mentioned on GitHubpytorchSyntology: not harvested report
oulutan/Drone_FasterRCNN mentioned on GitHubpytorchMITSyntology: not harvested report
quangvy2703/ABCNet-ESRGAN-SRTEXT mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
ricky40403/Fcos_seg mentioned on GitHubpytorchMITSyntology: 7 samples, 5 ran (2 instrument-failed) · 2 unverified report
rosinality/fcos-pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
ryota2425/maskrcnn-benchmark mentioned on GitHubpytorchMITSyntology: not harvested report
sarrrrry/maskrcnn-benchmark mentioned on GitHubpytorchMITSyntology: not harvested report
stigma0617/maskrcnn-benchmark-vovnet mentioned on GitHubpytorchMITSyntology: not harvested report
touchylk/fcoseccv mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
tuananh1007/Faster-R-CNN-and-Mask-R-CNN-in-PyTorch-1.0 mentioned on GitHubpytorchMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
vierachen/maskrcnn mentioned on GitHubpytorchMITSyntology: not harvested report
vov-net/VoVNet-FCOS mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
worldlife123/maskrcnn-benchmark mentioned on GitHubpytorchMITSyntology: not harvested report
wuyangzhang/maskrcnn mentioned on GitHubpytorchMITSyntology: not harvested report
xuannianz/keras-fcos mentioned on GitHubtfSyntology: not harvested report
xytpai/DetX-FCOS mentioned on GitHubpytorchSyntology: not harvested report
xytpai/fcos mentioned on GitHubpytorchMITSyntology: 6 samples, 6 ran (2 instrument-failed) · 0 unverified report
zhaozhijie1997/Unifed-Lane-and-Traffic-Sign-detection mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
zhongzisha/object_detection mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
zhubinQAQ/Ins mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
zy0851/FB-m-RCNN mentioned on GitHubpytorchMITSyntology: not harvested report
2023-MindSpore-1/ms-code-214 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code10 mindsporeSyntology: not harvested report
2024-MindSpore-1/Code5 mindsporeSyntology: not harvested report
Burf/tfdetection tfSyntology: 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), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified), Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation (arXiv:1802.02611; that paper's own run record: 44 ran (of which 17 constructed an object rather than computing a result; 28 with no instrument failure: 2 honoured, 0 violated, 26 with no contract checked; 16 where Syntology's instrument failed) · 28 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
MegEngine/Models Syntology: not harvested report
MindSpore-paper-code-3/code10 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code3 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code6 mindsporeSyntology: not harvested 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
alibaba/EasyCV pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to End-to-End Object Detection with Transformers (arXiv:2005.12872; that paper's own run record: 70 ran (of which 45 constructed an object rather than computing a result; 62 with no instrument failure: 2 honoured, 1 violated, 59 with no contract checked; 8 where Syntology's instrument failed) · 22 unverified), Training data-efficient image transformers & distillation through attention (arXiv:2012.12877; that paper's own run record: 12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified), Masked Autoencoders Are Scalable Vision Learners (arXiv:2111.06377; that paper's own run record: 86 ran (of which 40 constructed an object rather than computing a result; 68 with no instrument failure: 8 honoured, 0 violated, 60 with no contract checked; 18 where Syntology's instrument failed) · 51 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
code-implementation1/Code2 mindsporeSyntology: not harvested report
code-implementation1/Code9 mindsporeSyntology: 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
pytorch/vision pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Going Deeper with Convolutions (arXiv:1409.4842; that paper's own run record: 34 ran (of which 19 constructed an object rather than computing a result; 30 with no instrument failure: 1 honoured, 0 violated, 29 with no contract checked; 4 where Syntology's instrument failed) · 8 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), Deep Networks with Stochastic Depth (arXiv:1603.09382; that paper's own run record: 8 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified) and 7 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
srihari-humbarwadi/tensorflow_fcos tfApache-2.0Syntology: 6 samples, 6 ran (0 instrument-failed) · 0 unverified report
gitlab.com/birder/birder pytorchSyntology: 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

40 samples harvested: 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. “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.

2ran · honoured contract
2ran · violated contract
6ran · our draft was wrong
1ran; the contract check could not run
26ran
3unverified

Licence: 19 of the 40 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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. 1 sample is listed last, in a group without a repository. “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.

BIYTC/mobilenet_maskrcnn community (archive-listed) 4 samples, 4 ran (1 instrument-failed) · 0 unverified
get_group_gn in 5 papers maskrcnn_benchmark/modeling/make_layers.py ran MIT recorded; this copy not marked cleared · pointer only · 83c64313d0501174 · report fixture: signature dim:int/0/int, dim_per_gp:int/0/int, num_groups:int/0/int · returned int · level recorded 2026-09-25
interpolate in 95 papers maskrcnn_benchmark/layers/misc.py ran · our draft was wrong MIT recorded; this copy not marked cleared · pointer only · 2902bf4410253ff7 · report fixture: signature input:Tensor/4/float, size:tuple/1/int, scale_factor:NoneType/0/?, mode:str/0/str, align_corners:NoneType/0/? · returned Tensor · level recorded 2026-09-25
sigmoid_focal_loss_cpu in 18 papers maskrcnn_benchmark/layers/sigmoid_focal_loss.py ran MIT recorded; this copy not marked cleared · pointer only · c42eaa8eb1b704cd · report fixture: signature logits:Tensor/2/float, targets:Tensor/1/int, gamma:float/0/float, alpha:float/0/float · returned Tensor · level recorded 2026-09-24
smooth_l1_loss in 28 papers maskrcnn_benchmark/layers/smooth_l1_loss.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · e261fa29066b37e5 · report fixture: signature input:Tensor/2/float, target:Tensor/2/float, beta:float/0/float, size_average:bool/0/bool · returned Tensor · level recorded 2026-09-24
FluteXu/ms-project community (archive-listed) 1 sample, 0 ran · 1 unverified
build_roi_box_head in 8 papers build/lib.linux-x86_64-3.7/maskrcnn_benchmark/modeling/roi_heads/box_head/box_head.py unverified MIT (permissive) · cf6c9b5f6174fc81 · report
Iamal1/maskrcnn-benchmark community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
balanced_l1_loss maskrcnn_benchmark/layers/balanced_l1_loss.py ran MIT recorded; this copy not marked cleared · pointer only · cf6230491f9702dc · report fixture: signature pred:Tensor/2/float, target:Tensor/2/float, weight:Tensor/2/float, alpha:float/0/float, gamma:float/0/float, beta:float/0/float, avg_factor:NoneType/0/?, reduction:str/0/str · returned Tensor · level recorded 2026-09-24
l2_loss in 136 papers maskrcnn_benchmark/layers/l2_loss.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · 5ab322eae8b53480 · report fixture: signature input:Tensor/2/float, target:Tensor/2/float · returned Tensor · level recorded 2026-09-25
sigmoid_focal_loss_cpu in 18 papers maskrcnn_benchmark/layers/sigmoid_focal_loss.py ran MIT recorded; this copy not marked cleared · pointer only · 426fd02a2beaf826 · report fixture: signature logits:Tensor/2/float, targets:Tensor/1/int, gamma:Tensor/1/float, alpha:Tensor/1/float · returned Tensor · level recorded 2026-09-25
PeterTKovacs/zold137 community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
read_custom_dict drone_demo/custom_train.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · 84fb771ac13f3af1 · report fixture: signature file:str/0/str · returned dict · level recorded 2026-09-24
Zanderzt/TensorRT_Mask_RCNN community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
LR demo/zyw.py ran MIT recorded; this copy not marked cleared · pointer only · 0eaf951d3a22588b · report fixture: signature X_train:ndarray/2/float, X_test:ndarray/2/float, y_train:ndarray/1/float, y_test:ndarray/1/float · returned float · level recorded 2026-09-24
RF demo/zyw.py ran MIT recorded; this copy not marked cleared · pointer only · 00700fd67cb3e29a · report fixture: signature X_train:ndarray/2/float, X_test:ndarray/2/float, y_train:ndarray/1/float, y_test:ndarray/1/float · returned float · level recorded 2026-09-24
kohillyang/mx-detection community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
batch_fn scripts/train_fcos.py ran · honoured contract fingerprinted no licence file found · pointer only · d0b9e262619a0908 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
latentgnn/maskrcnn-benchmark-latentgnn community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
has_valid_annotation maskrcnn_benchmark/data/datasets/coco.py ran · violated contract MIT (permissive) · 2531c930ac17dddf · report fixture: signature anno:list/1/dict · returned bool · level recorded 2026-09-22
lijain/FCOS-change community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
reduce_sum in 34 papers
census: 4 implementations from 5 papers, 4 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 1 of 4, arg 1: rank 1, kind float, dtype float32
fcos_core/modeling/rpn/fcos/loss.py ran · violated contract fingerprinted no licence file found · pointer only · 73567c93e91cf2f7 · report fixture: signature tensor:Tensor/1/float · returned Tensor · level recorded 2026-09-22
markson14/WheatDet community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
format_prediction_string demo/wheat_inference.py ran MIT recorded; this copy not marked cleared · pointer only · 069333d11241eccd · report fixture: signature boxes:list/1/list, scores:list/1/float · returned str · level recorded 2026-09-24
ricky40403/Fcos_seg community (archive-listed) 7 samples, 5 ran (2 instrument-failed) · 2 unverified
conv1x1 in 691 papers Fcos_seg/backbone/resnet.py ran · our draft was wrong MIT (permissive) · d9def42110729a85 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
conv1x1 in 691 papers Fcos_seg/backbone/volvenet.py ran MIT (permissive) · 9e931093b7cb657e · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, module_name:str/0/str, postfix:str/0/str, stride:int/0/int, groups:int/0/int, kernel_size:int/0/int, padding:int/0/int · returned list · level recorded 2026-09-24
conv3x3 in 1,376 papers Fcos_seg/backbone/resnet.py ran · our draft was wrong MIT (permissive) · 160bb14bd76201b4 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int · returned Conv2d · level recorded, date not recorded
conv3x3 in 1,376 papers Fcos_seg/backbone/volvenet.py ran MIT (permissive) · 971b790fc16af272 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, module_name:str/0/str, postfix:str/0/str, stride:int/0/int, groups:int/0/int, kernel_size:int/0/int, padding:int/0/int · returned list · level recorded 2026-09-24
vovnet57 Fcos_seg/backbone/volvenet.py ran MIT (permissive) · f9f03971f1bab8c1 · report fixture: signature pretrained:bool/0/bool, progress:bool/0/bool · returned VoVNet · level recorded 2026-09-24
make_coco_detection Fcos_seg/core/coco_eval.py unverified MIT (permissive) · c5c7f9c741faf54d · report
resnet18 in 432 papers Fcos_seg/backbone/resnet.py unverified MIT (permissive) · fc9af2f2cc533781 · report
rosinality/fcos-pytorch community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
make_coco_detection evaluate.py ran · our draft was wrong MIT (permissive) · 96e93f6459e7f4bd · report fixture: signature predictions:list/1/Prediction, dataset:Dataset/0/? · returned list · level recorded 2026-09-22
tuananh1007/Faster-R-CNN-and-Mask-R-CNN-in-PyTorch-1.0 community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
expand_boxes in 5 papers maskrcnn_benchmark/modeling/roi_heads/mask_head/inference.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · 5362c4106bc79217 · report fixture: signature boxes:Tensor/2/float, scale:float/0/float · returned Tensor · level recorded 2026-09-24
expand_masks maskrcnn_benchmark/modeling/roi_heads/mask_head/inference.py ran MIT recorded; this copy not marked cleared · pointer only · 762ce037e4512c48 · report fixture: signature mask:Tensor/4/float, padding:int/0/int · returned tuple · level recorded 2026-09-25
project_masks_on_boxes maskrcnn_benchmark/modeling/roi_heads/mask_head/loss.py ran MIT recorded; this copy not marked cleared · pointer only · 7282d9e488dd0a6d · report fixture: signature segmentation_masks:SegmentationMaskList/0/?, proposals:MockBoxList/0/?, discretization_size:int/0/int · returned Tensor · level recorded 2026-09-25
xytpai/fcos community (archive-listed) 6 samples, 6 ran (2 instrument-failed) · 0 unverified
bbox_overlaps_aligned libs/iou_loss.py ran fingerprinted MIT (permissive) · 318c2c9407b81028 · report fixture: signature bboxes1:Tensor/2/float, bboxes2:Tensor/2/float, is_aligned:bool/0/bool · returned Tensor · level recorded 2026-09-24
conv3x3 in 1,376 papers backbone.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · fac5364e2f53c6db · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
get_loss in 107 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 4 of 4, arg 1: rank 2, kind float, dtype float32
detector.py ran · our draft was wrong fingerprinted MIT (permissive) · bafd66dce4d45e2a · report fixture: signature temp:Tensor/2/float · returned Tensor · level recorded 2026-09-22
iou_loss in 17 papers libs/iou_loss.py ran fingerprinted MIT (permissive) · dbd9612822534e83 · report fixture: signature pred:Tensor/2/float, target:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-24
resnet18 in 432 papers backbone.py ran MIT (permissive) · 66e10ac6440feae6 · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-24
resnet34 in 148 papers backbone.py ran MIT (permissive) · fabaffc1a606ef9b · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-24
zhongzisha/object_detection community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
nms in 65 papers train_FCOS.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 99d667302be1c9e3 · report fixture: signature dets:ndarray/2/float, thresh:float/0/float · returned list · level recorded 2026-09-22
srihari-humbarwadi/tensorflow_fcos community (archive-listed) 6 samples, 6 ran (0 instrument-failed) · 0 unverified
centerness_loss tensorflow_fcos/models/fcos/losses.py ran Apache-2.0 (permissive) · 987c1ea87f06ee22 · report fixture: signature labels:EagerTensor/2/float, logits:EagerTensor/2/float, fg_mask:EagerTensor/1/float, normalizer_value:EagerTensor/0/float · returned EagerTensor · level recorded 2026-09-24
conv_block in 95 papers tensorflow_fcos/models/blocks.py ran Apache-2.0 (permissive) · 43351463fea5b39a · report fixture: signature input_tensor:KerasTensor/0/float, filters:int/0/int, kernel_size:int/0/int, strides:int/0/int, padding:str/0/str, kernel_init:str/0/str, bias_init:str/0/str, bn_act:bool/0/bool, name_prefix:str/0/str · returned KerasTensor · level recorded 2026-09-24
draw_boxes_cv2 tensorflow_fcos/utils/visualization.py ran Apache-2.0 (permissive) · f900af0f07e48e3f · report fixture: signature image:ndarray/3/int, bbox_list:list/1/list, H:int/0/int, W:int/0/int · returned ndarray · level recorded 2026-09-24
focal_loss in 65 papers
census: 6 implementations from 13 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
tensorflow_fcos/models/fcos/losses.py ran Apache-2.0 (permissive) · fce50f2fda34fc22 · report fixture: signature y_true:EagerTensor/2/int, y_pred:EagerTensor/3/float, normalizer_value:EagerTensor/0/float, num_classes:int/0/int, alpha:float/0/float, gamma:float/0/float · returned EagerTensor · level recorded 2026-09-24
iou_loss in 17 papers tensorflow_fcos/models/fcos/losses.py ran Apache-2.0 (permissive) · 5e47641ad906ae7b · report fixture: signature labels:EagerTensor/3/float, logits:EagerTensor/3/float, centers:EagerTensor/3/float, fg_mask:EagerTensor/2/float, normalizer_value:EagerTensor/1/float · returned EagerTensor · level recorded 2026-09-24
upsample_like tensorflow_fcos/models/blocks.py ran Apache-2.0 (permissive) · 11565a347678ccac · report fixture: signature input_tensor:EagerTensor/4/float, target_tensor:EagerTensor/4/float, name:str/0/str · returned EagerTensor · level recorded 2026-09-24
Repository not located 1 sample, 1 ran (0 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
get_lr in 91 papers repository not located ran · honoured contract licence of this copy not recorded · 7337f1f5ff01dcd0 · report fixture: signature optimizer:SGD/0/? · returned float · level recorded, date not recorded

Tasks

2D Object DetectionObjectObject DetectionPedestrian DetectionSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
2D Object Detection SARDet-100K FCOS box mAP 49.8 #8 of 13 Archive leaderboard report
Object Detection COCO minival FCOS (ResNet-50-FPN + improvements) AP50 57.4 #193 of 220 Archive leaderboard report
Object Detection COCO minival FCOS (ResNet-50-FPN + improvements) AP75 41.4 #193 of 220 Archive leaderboard report
Object Detection COCO minival FCOS (ResNet-50-FPN + improvements) APL 49.8 #193 of 220 Archive leaderboard report
Object Detection COCO minival FCOS (ResNet-50-FPN + improvements) APM 42.5 #193 of 220 Archive leaderboard report
Object Detection COCO minival FCOS (ResNet-50-FPN + improvements) APS 22.3 #193 of 220 Archive leaderboard report
Object Detection COCO minival FCOS (ResNet-50-FPN + improvements) box AP 38.6 #193 of 220 Archive leaderboard report
Object Detection COCO test-dev FCOS (ResNeXt-64x4d-101-FPN 4 + improvements) AP50 64.1 #141 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (ResNeXt-64x4d-101-FPN 4 + improvements) AP75 48.4 #141 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (ResNeXt-64x4d-101-FPN 4 + improvements) APL 55.6 #141 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (ResNeXt-64x4d-101-FPN 4 + improvements) APM 47.5 #141 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (ResNeXt-64x4d-101-FPN 4 + improvements) APS 27.6 #141 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (ResNeXt-64x4d-101-FPN 4 + improvements) box mAP 44.7 #141 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (ResNeXt-101-64x4d-FPN) AP50 62.8 #161 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (ResNeXt-101-64x4d-FPN) AP75 46.6 #161 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (ResNeXt-101-64x4d-FPN) APL 53.3 #161 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (ResNeXt-101-64x4d-FPN) APM 46.2 #161 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (ResNeXt-101-64x4d-FPN) APS 26.5 #161 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (ResNeXt-101-64x4d-FPN) box mAP 43.2 #161 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (ResNeXt-32x8d-101-FPN) AP50 62.2 #171 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (ResNeXt-32x8d-101-FPN) AP75 46.1 #171 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (ResNeXt-32x8d-101-FPN) APL 52.6 #171 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (ResNeXt-32x8d-101-FPN) APM 45.6 #171 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (ResNeXt-32x8d-101-FPN) APS 26.0 #171 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (ResNeXt-32x8d-101-FPN) box mAP 42.7 #171 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (HRNet-W32-5l) AP50 60.4 #178 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (HRNet-W32-5l) AP75 45.3 #178 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (HRNet-W32-5l) APL 51.0 #178 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (HRNet-W32-5l) APM 45.0 #178 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (HRNet-W32-5l) APS 25.4 #178 of 225 Archive leaderboard report
Object Detection COCO test-dev FCOS (HRNet-W32-5l) box mAP 42.0 #178 of 225 Archive leaderboard report
Object Detection COCO-O FCOS (ResNet-50) Average mAP 16.7 #38 of 45 Archive leaderboard report
Object Detection COCO-O FCOS (ResNet-50) Effective Robustness 0.25 #38 of 45 Archive leaderboard report
Pedestrian Detection TJU-Ped-campus FCOS ALL (miss rate) 41.62 #3 of 4 Archive leaderboard report
Pedestrian Detection TJU-Ped-campus FCOS HO (miss rate) 81.28 #3 of 4 Archive leaderboard report
Pedestrian Detection TJU-Ped-campus FCOS R (miss rate) 31.89 #3 of 4 Archive leaderboard report
Pedestrian Detection TJU-Ped-campus FCOS R+HO (miss rate) 39.38 #3 of 4 Archive leaderboard report
Pedestrian Detection TJU-Ped-campus FCOS RS (miss rate) 69.04 #3 of 4 Archive leaderboard report
Pedestrian Detection TJU-Ped-traffic FCOS ALL (miss rate) 40.02 #6 of 6 Archive leaderboard report
Pedestrian Detection TJU-Ped-traffic FCOS HO (miss rate) 63.73 #6 of 6 Archive leaderboard report
Pedestrian Detection TJU-Ped-traffic FCOS R (miss rate) 24.35 #6 of 6 Archive leaderboard report
Pedestrian Detection TJU-Ped-traffic FCOS R+HO (miss rate) 28.86 #6 of 6 Archive leaderboard report
Pedestrian Detection TJU-Ped-traffic FCOS RS (miss rate) 37.40 #6 of 6 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: FCOS

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionFCOSFPNFocal LossGlobal Average PoolingGrouped ConvolutionKaiming InitializationLogistic RegressionMax PoolingNon Maximum SuppressionReLUResNeXtResNeXt BlockResidual BlockResidual ConnectionRetinaNetSGD with MomentumSSDWeight DecayYOLOv3k-Means Clustering

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