Papers › Focal Loss for Dense Object Detection

Focal Loss for Dense Object Detection

7 Aug 2017ICCV 2017 10arXiv:1708.02002archive 2025-07-28

Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, Piotr Dollár

The highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations. In contrast, one-stage detectors that are applied over a regular, dense sampling of possible object locations have the potential to be faster and simpler, but have trailed the accuracy of two-stage detectors thus far. In this paper, we investigate why this is the case. We discover that the extreme foreground-background class imbalance encountered during training of dense detectors is the central cause. We propose to address this class imbalance by reshaping the standard cross entropy loss such that it down-weights the loss assigned to well-classified examples. Our novel Focal Loss focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training. To evaluate the effectiveness of our loss, we design and train a simple dense detector we call RetinaNet. Our results show that when trained with the focal loss, RetinaNet is able to match the speed of previous one-stage detectors while surpassing the accuracy of all existing state-of-the-art two-stage detectors. Code is at: https://github.com/facebookresearch/Detectron.

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

No sample from the archive's official repository (facebookresearch/detectron) is linked to this paper; the 11 samples below come from 8 community repositories. Syntology harvested code from facebookresearch/detectron for 4 other papers.

facebookresearch/detectron: 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), 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), 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) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method.

Syntology 11 code samples harvested from 8 repositories linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 9 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 11 samples from 8 repositories, 11 ran (2 with no instrument failure; 9 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 29 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.

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

facebookresearch/detectron officialmentioned in papermentioned 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), 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), 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) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
497626895/darknet mentioned on GitHubtfSyntology: not harvested report
AdeelH/pytorch-multi-class-focal-loss mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
AlexeyAB/darknet mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
AtlasCoCo/Darknet mentioned on GitHubtfSyntology: not harvested report
CahideSara/deneme mentioned on GitHubtfSyntology: not harvested report
Chang-Chia-Chi/TrackNet-Badminton-Tracking-tensorflow2 mentioned on GitHubtfSyntology: not harvested report
ChristianMarzahl/ObjectDetection mentioned on GitHubpytorchSyntology: not harvested report
DInesh1234-wq/tyredataset mentioned on GitHubpytorchSyntology: not harvested report
DaloroAT/first_break_picking mentioned on GitHubpytorchSyntology: 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); nothing checks that they implement this paper's method. report
DetectionTeamUCAS/RetinaNet_Tensorflow_Rotation mentioned on GitHubtfSyntology: not harvested report
DonCorle0ne/damage_detection mentioned on GitHubSyntology: not harvested report
DrMMZ/RetinaNet mentioned on GitHubtfSyntology: not harvested report
EMsnap/RobotSorting mentioned on GitHubSyntology: not harvested report
FL77N/RetinaNet-Based-on-PPdet mentioned on GitHubpaddleSyntology: not harvested report
GXYM/Focal-loss mentioned on GitHubtfSyntology: not harvested report
Guillem96/efficient-net-tf mentioned on GitHubtfSyntology: not harvested report
Guillem96/efficientdet-tf mentioned on GitHubtfGPL-3.0Syntology: not harvested report
HongSic/DarknetAI mentioned on GitHubtfSyntology: not harvested report
IPLI/IPLI_Server mentioned on GitHubtfSyntology: not harvested report
IlyaOvodov/AngelinaReader mentioned on GitHubpytorchSyntology: not harvested report
JaryHuang/awesome_SSD_FPN_GIoU 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
Jo-dsa/SemanticSeg mentioned on GitHubpytorchSyntology: 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); nothing checks that they implement this paper's method. report
KingBoyBIT/yolov3test mentioned on GitHubSyntology: not harvested report
LIU1514/Yolov3- mentioned on GitHubtfSyntology: not harvested report
Lmath11/darknet mentioned on GitHubtfSyntology: not harvested report
MIC-DKFZ/DetectionAndRegression mentioned on GitHubpytorchSyntology: not harvested report
MIC-DKFZ/RegRCNN mentioned on GitHubpytorchSyntology: not harvested report
MariefW/6.-trainingYOLO mentioned on GitHubtfSyntology: not harvested report
Maskify/darknet mentioned on GitHubtfSyntology: not harvested report
NVIDIA/retinanet-examples 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
NovasMax/R3Det-Refined-Single-Stage-Detector-with-Feature-Refinement-for-RO mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object (arXiv:1908.05612; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
OFRIN/Tensorflow_RetinaFace mentioned on GitHubtfSyntology: not harvested report
PolarisAlpha/darknet mentioned on GitHubSyntology: not harvested report
Popoooo/darknet_test mentioned on GitHubtfSyntology: not harvested report
RichardMathewsII/YOLBO mentioned on GitHubSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverified report
RuoyuChen10/objectdetection-saliency-maps mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization (arXiv:1610.02391; that paper's own run record: 90 ran (of which 32 constructed an object rather than computing a result; 62 with no instrument failure: 6 honoured, 4 violated, 52 with no contract checked; 28 where Syntology's instrument failed) · 51 unverified); nothing checks that they implement this paper's method. report
SJTU-Thinklab-Det/r3det-on-mmdetection mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object (arXiv:1908.05612; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
SanketAgrawal/Catagorical-Focal-Loss mentioned on GitHubSyntology: not harvested report
ShaharrHorn/Detection-Game-logic mentioned on GitHubSyntology: not harvested report
ShaojieJiang/tldr mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to TLDR: Token Loss Dynamic Reweighting for Reducing Repetitive Utterance Generation (arXiv:2003.11963; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
Shraddha2013/customyolo mentioned on GitHubtfSyntology: not harvested report
Shraddha2013/darknett mentioned on GitHubtfSyntology: not harvested report
Shraddha2013/darknetyol mentioned on GitHubtfSyntology: not harvested report
Shraddha2013/darknetyolo mentioned on GitHubtfSyntology: not harvested report
Shraddha2013/darknetyolo3 mentioned on GitHubtfSyntology: not harvested report
Shraddha2013/mydarknetyolo mentioned on GitHubtfSyntology: not harvested report
Shraddha2013/myfileyolo mentioned on GitHubtfSyntology: not harvested report
Stephenfang51/Focal_loss_turtorial mentioned on GitHubpytorchSyntology: not harvested report
Suci2609/generate_train_list.py- mentioned on GitHubtfSyntology: not harvested report
Sushma07/dancedarknet mentioned on GitHubtfSyntology: not harvested report
Techyee/darknet_resource mentioned on GitHubtfSyntology: not harvested report
Thinklab-SJTU/CSL_RetinaNet_Tensorflow mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
ViswanathaReddyGajjala/EfficientNet-RetinaNet mentioned on GitHubpytorchSyntology: not harvested report
Viveksbawa/SARAS-ESAD-Baseline mentioned on GitHubpytorchSyntology: not harvested report
Wangxy2180/darknetKinectDetect mentioned on GitHubtfSyntology: not harvested report
YIZHE12/fashiontags mentioned on GitHubtfSyntology: not harvested report
YIZHE12/robots mentioned on GitHubSyntology: not harvested report
Yashgh7076/Eluvio-ML-Scene-Segmentation mentioned on GitHubpytorchSyntology: not harvested report
Yonder-OSS/D3M-Primitives mentioned on GitHubtfSyntology: not harvested report
ZTao-z/multiflow-resnet-ssd mentioned on GitHubpytorchSyntology: not harvested report
ZhenJie-Zhang/darknet_shoe mentioned on GitHubtfSyntology: not harvested report
aakashjhawar/traffic-sign-detection mentioned on GitHubtfSyntology: not harvested report
agutuyen-dev/darknet mentioned on GitHubtfSyntology: not harvested report
ahhan02/darknet-alex mentioned on GitHubtfSyntology: not harvested report
aminekha/AI-For-2022 mentioned on GitHubtfSyntology: not harvested report
amittiwary42/target-detection-eeg-signals mentioned on GitHubSyntology: not harvested report
annabellachen/newDarknet mentioned on GitHubtfSyntology: not harvested report
anookeen/yolo mentioned on GitHubSyntology: not harvested report
artemmavrin/focal-loss mentioned on GitHubtfSyntology: not harvested report
artxtech/darknet-rnn mentioned on GitHubtfSyntology: not harvested report
artynet/darknet-alexeyAB mentioned on GitHubtfSyntology: not harvested report
ayushpalak/darknet_cokebottles mentioned on GitHubSyntology: not harvested report
ayushpalak/darknet_multi_cokebottles mentioned on GitHubSyntology: not harvested report
benihime91/pytorch_retinanet mentioned on GitHubpytorchSyntology: not harvested report
bharatsush/object_detection mentioned on GitHubSyntology: not harvested report
binhdv92/darknet mentioned on GitHubtfSyntology: not harvested report
binhdv92/darknet_kriyeng mentioned on GitHubtfSyntology: not harvested report
bobby20180331/darknet_pycharm mentioned on GitHubSyntology: not harvested report
buptdbj/darknet-windows-linux mentioned on GitHubSyntology: not harvested report
caihaocong/Yolov3_AlexeyAB_Version mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to YOLO9000: Better, Faster, Stronger (arXiv:1612.08242; that paper's own run record: 44 ran (of which 0 constructed an object rather than computing a result; 33 with no instrument failure: 1 honoured, 4 violated, 28 with no contract checked; 11 where Syntology's instrument failed) · 16 unverified); nothing checks that they implement this paper's method. report
cameronchoi/r3det-copy mentioned on GitHubpytorchnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
cloudnine148/PHC_2nd_SPC mentioned on GitHubSyntology: not harvested report
csm-kr/Retinanet_pytorch mentioned on GitHubpytorchSyntology: not harvested report
darshans0200/YOLOTest mentioned on GitHubSyntology: not harvested report
daveboat/pytorch_focal_loss mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
dc17540/darknet mentioned on GitHubtfSyntology: not harvested report
delmalih/MIAS-mammography-obj-detection mentioned on GitHubpytorchSyntology: not harvested report
detectionteamucas/retinanet_tensorflow mentioned on GitHubtfSyntology: not harvested report
dishen12/py03 mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Receptive Field Block Net for Accurate and Fast Object Detection (arXiv:1711.07767; that paper's own run record: 3 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; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
dtthi/darknetAlexeyAB mentioned on GitHubtfSyntology: not harvested report
dwaithe/darknet3AB mentioned on GitHubtfSyntology: not harvested report
e0015274/darknet mentioned on GitHubtfSyntology: not harvested report
edgarrt/custom_darknet mentioned on GitHubtfSyntology: not harvested report
edwardclem/deepscribe mentioned on GitHubpytorchSyntology: not harvested report
eric-erki/darknet mentioned on GitHubSyntology: not harvested report
eric-erki/yolov3 mentioned on GitHubSyntology: not harvested report
ermuur/darknet mentioned on GitHubSyntology: not harvested report
fabiofumarola/ultrayolo mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to 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
feidfoe/AdjustBnd4Imbalance mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Adjusting Decision Boundary for Class Imbalanced Learning (arXiv:1912.01857; that paper's own run record: 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) · 0 unverified); nothing checks that they implement this paper's method. report
fizyr/keras-retinanet mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Improving RetinaNet for CT Lesion Detection with Dense Masks from Weak RECIST Labels (arXiv:1906.02283; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
fznsakib/great-ape-behaviour-detector mentioned on GitHubpytorchSyntology: not harvested report
ghadahamed/darknet mentioned on GitHubtfSyntology: not harvested report
ghaniskn/GCorp-Darknet mentioned on GitHubSyntology: not harvested report
gokulprasadthekkel/pytorch-multi-class-focal-loss mentioned on GitHubpytorchSyntology: not harvested report
gyes00205/waymo_tf_object_detection mentioned on GitHubtfSyntology: not harvested report
haithink/myWindowsDarknet mentioned on GitHubSyntology: not harvested report
hamzaMahdi/darknet mentioned on GitHubtfSyntology: not harvested report
hankpark0706/darknet mentioned on GitHubSyntology: not harvested report
hhuaibo/darknet mentioned on GitHubtfSyntology: not harvested report
hisiter97/darknet mentioned on GitHubtfSyntology: not harvested report
huytranvan2010/RetinaNet-Understanding mentioned on GitHubSyntology: not harvested report
hweersot/darknet-custom mentioned on GitHubtfSyntology: not harvested report
hyang0129/foodclassapp mentioned on GitHubtfApache-2.0Syntology: not harvested report
iskandari/darknet mentioned on GitHubtfSyntology: not harvested report
istvanmegyeri/audio_tagging mentioned on GitHubSyntology: not harvested report
ivanwilliammd/I3DR-Net-Transfer-Learning mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset (arXiv:1705.07750; that paper's own run record: 16 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 12 unverified); nothing checks that they implement this paper's method. report
jfc4050/detect-to-track 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
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
joheras/darknet-colab mentioned on GitHubtfSyntology: not harvested report
jolibrain/caffe mentioned on GitHubSyntology: not harvested report
juergenlandauer/Maya-Challenge mentioned on GitHubpytorchSyntology: not harvested report
kalelpark/ral mentioned on GitHubpytorchSyntology: not harvested report
karan96/NewOne mentioned on GitHubtfSyntology: not harvested report
kawshik8/DL-project mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Self-Supervised Learning of Pretext-Invariant Representations (arXiv:1912.01991; that paper's own run record: 3 ran (of which 3 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; every one of the 3 samples that ran constructed an object rather than computing a result) and A Simple Framework for Contrastive Learning of Visual Representations (arXiv:2002.05709; that paper's own run record: 115 ran (of which 33 constructed an object rather than computing a result; 89 with no instrument failure: 1 honoured, 1 violated, 87 with no contract checked; 26 where Syntology's instrument failed) · 22 unverified); nothing checks that they implement this paper's method. report
khaled2ahmed/k2a mentioned on GitHubtfSyntology: not harvested report
kongzhiyou/darknet-master mentioned on GitHubtfSyntology: not harvested report
kuangliu/pytorch-fpn 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
kvijaykrish/Bosch_AI_VehicleClassification mentioned on GitHubtfSyntology: not harvested report
kyunghwan/darknet_v3 mentioned on GitHubSyntology: not harvested report
lhcezx/Graph-FPN mentioned on GitHubtfSyntology: not harvested report
li-yibing/oceannet mentioned on GitHubSyntology: not harvested report
liyemei/Deformable-active-convolutional mentioned on GitHubSyntology: not harvested report
llsouder/screen-ocr mentioned on GitHubSyntology: not harvested report
lyk19940625/MyRFBNet mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications (arXiv:1704.04861; that paper's own run record: 53 ran (of which 28 constructed an object rather than computing a result; 44 with no instrument failure: 4 honoured, 0 violated, 40 with no contract checked; 9 where Syntology's instrument failed) · 30 unverified); nothing checks that they implement this paper's method. report
magnificent1208/r3det-on-mmdetection mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
manishravula/yolov3_tiny_pruned mentioned on GitHubSyntology: not harvested report
mathieuorhan/darknet mentioned on GitHubSyntology: not harvested report
mdv3101/darknet-yolov3 mentioned on GitHubSyntology: not harvested report
mic-dkfz/medicaldetectiontoolkit mentioned on GitHubpytorchSyntology: not harvested report
minhdua/PHONES mentioned on GitHubtfSyntology: not harvested report
mkocabas/focal-loss-keras mentioned on GitHubtfSyntology: not harvested report
moallafatma/Breast_Cancer_Detection_Classification mentioned on GitHubpytorchSyntology: not harvested report
namdvt/Focal-loss-pytorch-implementation mentioned on GitHubpytorchSyntology: not harvested report
neshitov/UNet mentioned on GitHubpytorchSyntology: not harvested report
nguoido/Yolo-alexeyAB mentioned on GitHubtfSyntology: not harvested report
oorrppp2/darknet-pose mentioned on GitHubtfSyntology: not harvested report
patelmiteshn/darknet mentioned on GitHubSyntology: not harvested report
pengrenlai/RetinaNet-tensorflow mentioned on GitHubtfSyntology: not harvested report
petrum01/Capstone_project_object_detection mentioned on GitHubtfSyntology: not harvested report
pierluigiferrari/ssd_keras mentioned on GitHubtfSyntology: not harvested report
ppokhare/Handling-Imbalanced-Dataset-for-classification-task mentioned on GitHubSyntology: not harvested report
qingyujean/Classification-on-imbalanced-data mentioned on GitHubtfSyntology: not harvested report
rahowa/catboost_focal_loss mentioned on GitHubSyntology: not harvested report
rainofmine/Face_Attention_Network mentioned on GitHubpytorchSyntology: not harvested report
raspstephan/sugar-flower-fish-or-gravel mentioned on GitHubSyntology: not harvested report
rebeccagio/object_detection mentioned on GitHubSyntology: not harvested report
rnirdhar/yoloMultiClass mentioned on GitHubSyntology: not harvested report
rnirdhar/yoloTestOneClass mentioned on GitHubSyntology: not harvested report
ruinmessi/RFBNet mentioned on GitHubpytorchSyntology: not harvested report
ryubidragonfire/mydarknet mentioned on GitHubSyntology: not harvested report
saber2011/darknet mentioned on GitHubtfSyntology: not harvested report
saednasir/Helmet_Yolo mentioned on GitHubSyntology: not harvested report
samsonadmin/modified-alexeyab-darknet mentioned on GitHubtfSyntology: not harvested report
sdu2011/darknet_alexyab mentioned on GitHubtfSyntology: not harvested report
shashigharti/secure-privateai-scholarship-challenge mentioned on GitHubpytorchSyntology: not harvested report
sidify/resnet_focal_loss mentioned on GitHubSyntology: not harvested report
simonlevine/11785-project mentioned on GitHubpytorchSyntology: not harvested report
simonlevine/clinical-longformer mentioned on GitHubpytorchSyntology: not harvested report
skbadhsm/darknet2 mentioned on GitHubtfSyntology: not harvested report
soccergame/darknet mentioned on GitHubSyntology: not harvested report
solapark/da_yolo mentioned on GitHubtfSyntology: not harvested report
solapark/darknet_interpark mentioned on GitHubtfSyntology: not harvested report
solapark/darknet_partdet mentioned on GitHubtfSyntology: not harvested report
solapark/darknet_partdet_tmp mentioned on GitHubtfSyntology: not harvested report
stevenzhou2017/darknet_AlexeyAB mentioned on GitHubtfSyntology: not harvested report
sudharavali/objectDetectionYOLO mentioned on GitHubtfSyntology: not harvested report
sulasen/race-events-recognition-1 mentioned on GitHubtfSyntology: not harvested report
tallysprado/myDarknet mentioned on GitHubtfSyntology: not harvested report
teemoeric/projet mentioned on GitHubSyntology: not harvested report
tensorflow/models mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 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), 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) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
tianhai123/yolov3 mentioned on GitHubSyntology: not harvested report
toufiksk/darknet mentioned on GitHubSyntology: not harvested report
travismyers19/Vulnerable_Buildings mentioned on GitHubtfSyntology: not harvested report
trongnghia00/darknet mentioned on GitHubSyntology: not harvested report
tryolabs/luminoth mentioned on GitHubtfSyntology: not harvested report
unsky/RetinaNet mentioned on GitHubmxnetSyntology: not harvested report
unsky/focal-loss mentioned on GitHubmxnetSyntology: not harvested report
vantupham/darknet mentioned on GitHubSyntology: not harvested report
viethungluu/OCRetina mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
vuongtrannguyenkhoi/darknet mentioned on GitHubSyntology: not harvested report
wangxianhao/Improved-YOLOv3-for-UAV mentioned on GitHubSyntology: not harvested report
williamccondori/YOLO-NFPA mentioned on GitHubSyntology: not harvested report
witwickey/darknet mentioned on GitHubtfSyntology: not harvested report
wodyjowski/colab-training mentioned on GitHubtfSyntology: not harvested report
xiamenwcy/extended-caffe mentioned on GitHubSyntology: not harvested report
xuanyuzhou98/SqueezeSeg mentioned on GitHubtfBSD-2-ClauseSyntology: not harvested report
xytpai/retinanet mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
yhenon/pytorch-retinanet mentioned on GitHubpytorchSyntology: not harvested report
yijiaceline/Final-Project-Group4 mentioned on GitHubpytorchSyntology: not harvested report
yiningzeng/darknet-fork-from-AlexeyAB mentioned on GitHubtfSyntology: not harvested report
yudie433/darknet mentioned on GitHubSyntology: not harvested report
yuliani29/yolotraining mentioned on GitHubSyntology: not harvested report
yytang2012/darknet mentioned on GitHubSyntology: not harvested report
zhongzisha/object_detection mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
zj463261929/darknet_mAP mentioned on GitHubSyntology: not harvested report
zzhuolun/IRL mentioned on GitHubpytorchSyntology: not harvested report
2023-MindSpore-1/ms-code-216 mindsporeSyntology: not harvested report
2023-MindSpore-1/ms-code-216 mindsporeSyntology: not harvested report
2023-MindSpore-1/ms-code-223 mindsporeSyntology: not harvested report
2023-MindSpore-1/ms-code-44 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code10 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code11 mindsporeSyntology: not harvested report
2024-MindSpore-1/Code4 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DeepTextMark: A Deep Learning-Driven Text Watermarking Approach for Identifying Large... (arXiv:2305.05773; 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
2024-MindSpore-1/Code4 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DeepTextMark: A Deep Learning-Driven Text Watermarking Approach for Identifying Large... (arXiv:2305.05773; 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
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
CycloneBoy/PPDetectionPytorch pytorchSyntology: not harvested report
ENSTA-U2IS-AI/torch-uncertainty pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles (arXiv:1612.01474; that paper's own run record: 10 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified), mixup: Beyond Empirical Risk Minimization (arXiv:1710.09412; that paper's own run record: 36 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 22 where Syntology's instrument failed) · 11 unverified), Laplace Redux -- Effortless Bayesian Deep Learning (arXiv:2106.14806; that paper's own run record: 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) · 4 unverified) and 2 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
Mind23-2/MindCode-176 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code5 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code5 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
facebookresearch/detectron2 pytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
kornia/kornia pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer (arXiv:2110.02178; that paper's own run record: 53 ran (of which 31 constructed an object rather than computing a result; 44 with no instrument failure: 1 honoured, 0 violated, 43 with no contract checked; 9 where Syntology's instrument failed) · 15 unverified); nothing checks that they implement this paper's method. report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; 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) · 1 unverified); nothing checks that they implement this paper's method. report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; 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) · 1 unverified); nothing checks that they implement this paper's method. 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_retinanet tfSyntology: not harvested 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

11 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 9 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.

2ran · violated contract
5ran · our draft was wrong
4ran; the contract check could not run

Licence: 6 of the 11 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 8 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 whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

AdeelH/pytorch-multi-class-focal-loss community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
focal_loss in 65 papers
census: 6 implementations from 13 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
focal_loss.py ran · our draft was wrong MIT (permissive) · aa6467d64911f0e4 · report fixture: signature alpha:list/1/float, gamma:float/0/float, reduction:str/0/str, ignore_index:int/0/int, device:str/0/str, dtype:dtype/0/? · returned FocalLoss · level recorded 2026-09-22
RichardMathewsII/YOLBO community (archive-listed) 3 samples, 3 ran (2 instrument-failed) · 0 unverified
bb_center look_back.py ran · violated contract fingerprinted no licence file found · pointer only · 930423fe062e034a · report fixture: signature box:ndarray/1/float · returned tuple · level recorded 2026-09-22
centerBox look_back.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 8cdfe1aec1da011c · report fixture: signature box:ndarray/1/float, cb_ratio:float/0/float · returned ndarray · level recorded 2026-09-22
look_back look_back.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 41f3747438406647 · report fixture: signature box:ndarray/1/float, label:int/0/int, previous_matrix:ndarray/3/float · returned float64 · level recorded 2026-09-22
Thinklab-SJTU/CSL_RetinaNet_Tensorflow community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
get_gtboxes_and_label tools/multi_gpu_train.py ran · our draft was wrong Apache-2.0 (permissive) · b07dc7faf9668206 · report fixture: signature gtboxes_and_label_h:ndarray/2/float, gtboxes_and_label_r:ndarray/2/float, num_objects:int/0/int · returned tuple · level recorded 2026-09-22
daveboat/pytorch_focal_loss community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
focal_loss in 65 papers
census: 6 implementations from 13 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
focalloss.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · 6f5a902a2510561a · report fixture: signature input:Tensor/2/float, target:Tensor/1/int, gamma:float/0/float, eps:float/0/float, with_logits:bool/0/bool, ignore_index:int/0/int, reduction:str/0/str · returned Tensor · level recorded 2026-09-22
viethungluu/OCRetina community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
squeeze_last2dims_shape onestage/keras_retinanet/models/retinanet.py ran · violated contract fingerprinted no licence file found · pointer only · 7de75ab446b29075 · report fixture: signature x4d_shape:tuple/1/int · returned tuple · level recorded 2026-09-22
xytpai/retinanet community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
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
zhongzisha/object_detection community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
nms in 65 papers train_FCOS.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted licence of this copy not recorded · 99d667302be1c9e3 · report fixture: signature dets:ndarray/2/float, thresh:float/0/float · returned list · level recorded 2026-09-22
facebookresearch/detectron2 community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
ciou_loss in 6 papers detectron2/layers/losses.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · cee8870d4fbccc39 · report fixture: signature boxes1:Tensor/2/float, boxes2:Tensor/2/float, reduction:str/0/str, eps:float/0/float · returned Tensor · level recorded 2026-09-22
diou_loss in 5 papers detectron2/layers/losses.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 26f3066ead0d2eec · report fixture: signature boxes1:Tensor/2/float, boxes2:Tensor/2/float, reduction:str/0/str, eps:float/0/float · returned Tensor · level recorded 2026-09-22

Tasks

2D Object DetectionDense Object DetectionKnowledge DistillationLong-tail LearningObjectObject DetectionPedestrian DetectionReal-Time Object DetectionRegion Proposal

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
2D Object Detection SARDet-100K RetinaNet box mAP 47.4 #11 of 13 Archive leaderboard report
Dense Object Detection SKU-110K RetinaNet AP 45.5 #5 of 5 Archive leaderboard report
Dense Object Detection SKU-110K RetinaNet AP75 .389 #5 of 5 Archive leaderboard report
Face Identification Trillion Pairs Dataset F-Softmax Accuracy 39.80 #5 of 6 Archive leaderboard report
Face Verification Trillion Pairs Dataset F-Softmax Accuracy 37.14 #5 of 6 Archive leaderboard report
Long-tail Learning COCO-MLT Focal Loss(ResNet-50) Average mAP 49.46 #8 of 13 Archive leaderboard report
Long-tail Learning EGTEA Focal loss (3D- ResNeXt101) Average Precision 59.09 #3 of 3 Archive leaderboard report
Long-tail Learning EGTEA Focal loss (3D- ResNeXt101) Average Recall 59.17 #3 of 3 Archive leaderboard report
Long-tail Learning VOC-MLT Focal Loss(ResNet-50) Average mAP 73.88 #10 of 13 Archive leaderboard report
Object Counting CARPK RetinaNet (2018) MAE 24.58 #12 of 15 Archive leaderboard report
Object Detection COCO test-dev RetinaNet (ResNeXt-101-FPN) AP50 61.1 #188 of 225 Archive leaderboard report
Object Detection COCO test-dev RetinaNet (ResNeXt-101-FPN) AP75 44.1 #188 of 225 Archive leaderboard report
Object Detection COCO test-dev RetinaNet (ResNeXt-101-FPN) APL 51.2 #188 of 225 Archive leaderboard report
Object Detection COCO test-dev RetinaNet (ResNeXt-101-FPN) APM 44.2 #188 of 225 Archive leaderboard report
Object Detection COCO test-dev RetinaNet (ResNeXt-101-FPN) APS 24.1 #188 of 225 Archive leaderboard report
Object Detection COCO test-dev RetinaNet (ResNeXt-101-FPN) Hardware Burden 4G #188 of 225 Archive leaderboard report
Object Detection COCO test-dev RetinaNet (ResNeXt-101-FPN) box mAP 40.8 #188 of 225 Archive leaderboard report
Object Detection COCO test-dev RetinaNet (ResNet-101-FPN) AP50 59.1 #208 of 225 Archive leaderboard report
Object Detection COCO test-dev RetinaNet (ResNet-101-FPN) AP75 42.3 #208 of 225 Archive leaderboard report
Object Detection COCO test-dev RetinaNet (ResNet-101-FPN) APL 50.2 #208 of 225 Archive leaderboard report
Object Detection COCO test-dev RetinaNet (ResNet-101-FPN) APM 42.7 #208 of 225 Archive leaderboard report
Object Detection COCO test-dev RetinaNet (ResNet-101-FPN) APS 21.8 #208 of 225 Archive leaderboard report
Object Detection COCO test-dev RetinaNet (ResNet-101-FPN) Hardware Burden 4G #208 of 225 Archive leaderboard report
Object Detection COCO test-dev RetinaNet (ResNet-101-FPN) box mAP 39.1 #208 of 225 Archive leaderboard report
Object Detection COCO-O RetinaNet (ResNet-50) Average mAP 16.6 #39 of 45 Archive leaderboard report
Object Detection COCO-O RetinaNet (ResNet-50) Effective Robustness 0.18 #39 of 45 Archive leaderboard report
Pedestrian Detection TJU-Ped-campus RetinaNet ALL (miss rate) 44.34 #4 of 4 Archive leaderboard report
Pedestrian Detection TJU-Ped-campus RetinaNet HO (miss rate) 71.31 #4 of 4 Archive leaderboard report
Pedestrian Detection TJU-Ped-campus RetinaNet R (miss rate) 34.73 #4 of 4 Archive leaderboard report
Pedestrian Detection TJU-Ped-campus RetinaNet R+HO (miss rate) 42.26 #4 of 4 Archive leaderboard report
Pedestrian Detection TJU-Ped-campus RetinaNet RS (miss rate) 82.99 #4 of 4 Archive leaderboard report
Pedestrian Detection TJU-Ped-traffic RetinaNet ALL (miss rate) 41.40 #5 of 6 Archive leaderboard report
Pedestrian Detection TJU-Ped-traffic RetinaNet HO (miss rate) 61.60 #5 of 6 Archive leaderboard report
Pedestrian Detection TJU-Ped-traffic RetinaNet R (miss rate) 23.89 #5 of 6 Archive leaderboard report
Pedestrian Detection TJU-Ped-traffic RetinaNet R+HO (miss rate) 28.45 #5 of 6 Archive leaderboard report
Pedestrian Detection TJU-Ped-traffic RetinaNet RS (miss rate) 37.92 #5 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: Focal Loss, RetinaNet

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionFPNFocal LossGlobal Average PoolingGrouped ConvolutionKaiming InitializationMax PoolingRandom Horizontal FlipReLUResNeXtResNeXt BlockResidual BlockResidual ConnectionRetinaNetSGD with MomentumSPEEDWeight Decay

1 archive method tag without a method page not shown.

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