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 Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1904.01355")

Code

Syntology Ran 13 of 40 code samples harvested from 15 repositories linked to this paper; 27 have no recorded run. Of those that ran: 2 ran · honoured contract; 2 ran · violated contract; 5 ran · our draft was wrong; 1 ran · fixture could not drive it; 3 ran with no contract checked.

By repository: community (archive-listed): 39 samples from 15 repositories, 12 ran; 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.

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

tianzhi0549/FCOS officialmentioned on GitHubpytorchNOASSERTION report
yqyao/FCOS_PLUS mentioned in paperpytorchNOASSERTION report
Adelaide-AI-Group/FCOS mentioned on GitHubpytorchNOASSERTION report
BIYTC/mobilenet_maskrcnn mentioned on GitHubpytorchMIT report
DetectionTeamUCAS/FCOS_GluonCV mentioned on GitHubmxnetApache-2.0 report
FluteXu/ms-project mentioned on GitHubpytorch report
GuoLiuFang/maskrcnn-benchmark-lfs mentioned on GitHubpytorchMIT report
HRNet/HRNet-FCOS mentioned on GitHubpytorch report
Iamal1/maskrcnn-benchmark mentioned on GitHubpytorchMIT report
MalongTech/research-fad mentioned on GitHubpytorchNOASSERTION report
Mind23-2/MindCode-46 mentioned on GitHubmindspore report
Mind23-2/MindCode-47 mentioned on GitHubmindspore report
Miracle1991/DetectionHub mentioned on GitHubpytorch report
OFRIN/Tensorflow_FCOS mentioned on GitHubtf report
PeterTKovacs/zold137 mentioned on GitHubpytorchMIT report
Pxtri2156/AdelaiDet_v2 mentioned on GitHubpytorch report
SilvioGiancola/maskrcnn-benchmark mentioned on GitHubpytorchMIT report
Yuxiang1995/ICDAR2021_MFD mentioned on GitHubpytorchApache-2.0 report
Zanderzt/TensorRT_Mask_RCNN mentioned on GitHubpytorchMIT report
ZhZiKai/VisDrone_FCOS mentioned on GitHubpytorchNOASSERTION report
Zhang-Jing-Xuan/MaskRCNN mentioned on GitHubpytorchnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-ready report
Zhangyongtao123/maskrcnn_benchmark mentioned on GitHubpytorchMIT report
abcxs/maskrcnn-contest mentioned on GitHubpytorchMIT report
aim-uofa/AdelaiDet mentioned on GitHubpytorchNOASSERTION report
aim-uofa/adet mentioned on GitHubpytorch report
alannguyencs/maskrcnn mentioned on GitHubpytorchMIT report
aotumanbiu/awesome-object-detection mentioned on GitHubpytorch report
banben/maskrcnn-benchmark mentioned on GitHubpytorchMIT report
basaltzhang/maskrcnn-benchmark mentioned on GitHubpytorchMIT report
bimsarapathiraja/mccl mentioned on GitHubpytorchNOASSERTION report
blueardour/AdelaiDet mentioned on GitHubpytorchNOASSERTION report
ccchang1023/maskrcnn-benchmark mentioned on GitHubpytorchMIT report
chencq1234/maskrcnn_facebook mentioned on GitHubpytorchMIT report
cshizhe/maskrcnn_benchmark mentioned on GitHubpytorchMIT report
cyctrung/DPnet mentioned on GitHubpytorchMIT report
delmalih/MIAS-mammography-obj-detection mentioned on GitHubpytorch report
fcakyon/sahi-benchmark mentioned on GitHubpytorchMIT report
feng-lab/nuclei mentioned on GitHubpytorchMIT report
jahutwb/DL_dosimetry mentioned on GitHubpytorchMIT report
jonvthvn90/Project mentioned on GitHubpytorchMIT report
kohillyang/mx-detection mentioned on GitHubmxnet report
latentgnn/maskrcnn-benchmark-latentgnn mentioned on GitHubpytorch report
lijain/FCOS-change mentioned on GitHubpytorch report
lipengfeizju/Detection mentioned on GitHubpytorchMIT report
lipengyuMachineLearner/FCOS mentioned on GitHubpytorchNOASSERTION report
lippman1125/maskrcnn_benchmark_mobilenetv2 mentioned on GitHubpytorchMIT report
lzrobots/dgmn mentioned on GitHubpytorchMIT report
markson14/WheatDet mentioned on GitHubpytorchMIT report
monk-ai/maskrcnn mentioned on GitHubpytorchMIT report
neilctwu/FCOS-pytorch_Simplified mentioned on GitHubpytorch report
oulutan/Drone_FasterRCNN mentioned on GitHubpytorchMIT report
quangvy2703/ABCNet-ESRGAN-SRTEXT mentioned on GitHubpytorchNOASSERTION report
ricky40403/Fcos_seg mentioned on GitHubpytorchMIT report
rosinality/fcos-pytorch mentioned on GitHubpytorch report
ryota2425/maskrcnn-benchmark mentioned on GitHubpytorchMIT report
sarrrrry/maskrcnn-benchmark mentioned on GitHubpytorchMIT report
stigma0617/maskrcnn-benchmark-vovnet mentioned on GitHubpytorchMIT report
touchylk/fcoseccv mentioned on GitHubpytorchNOASSERTION report
vierachen/maskrcnn mentioned on GitHubpytorchMIT report
vov-net/VoVNet-FCOS mentioned on GitHubpytorchNOASSERTION report
worldlife123/maskrcnn-benchmark mentioned on GitHubpytorchMIT report
wuyangzhang/maskrcnn mentioned on GitHubpytorchMIT report
xuannianz/keras-fcos mentioned on GitHubtf report
xytpai/DetX-FCOS mentioned on GitHubpytorch report
xytpai/fcos mentioned on GitHubpytorchMIT report
zhaozhijie1997/Unifed-Lane-and-Traffic-Sign-detection mentioned on GitHubpytorchNOASSERTION report
zhongzisha/object_detection mentioned on GitHubtf report
zhubinQAQ/Ins mentioned on GitHubpytorchNOASSERTION report
zy0851/FB-m-RCNN mentioned on GitHubpytorchMIT report
open-mmlab/mmdetection pytorchApache-2.0 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.

Code Syntology ran Syntology

40 samples harvested; 13 ran; 2 honoured the contract we drafted; 27 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
2ran · violated contract
5ran · our draft was wrong
1ran · fixture could not drive it
3ran
27unverified

Licence: 18 of the 40 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 15 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

batch_fn kohillyang/mx-detection/scripts/train_fcos.py community (archive-listed) ran · honoured contract fingerprinted no licence file found · pointer only · d0b9e262619a0908 · report
conv1x1 ricky40403/Fcos_seg/Fcos_seg/backbone/resnet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · d9def42110729a85 · report
conv3x3 ricky40403/Fcos_seg/Fcos_seg/backbone/resnet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 160bb14bd76201b4 · report
conv3x3 xytpai/fcos/backbone.py community (archive-listed) ran · our draft was wrong MIT (permissive) · fac5364e2f53c6db · report
expand_boxes tuananh1007/Faster-R-CNN-and-Mask-R-CNN-in-PyTorch-1.0/maskrcnn_benchmark/modeling/roi_heads/mask_head/inference.py community (archive-listed) ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · 5362c4106bc79217 · report
get_loss xytpai/fcos/detector.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · bafd66dce4d45e2a · report
has_valid_annotation latentgnn/maskrcnn-benchmark-latentgnn/maskrcnn_benchmark/data/datasets/coco.py community (archive-listed) ran · violated contract MIT (permissive) · 2531c930ac17dddf · report
make_coco_detection rosinality/fcos-pytorch/evaluate.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 96e93f6459e7f4bd · report
nms zhongzisha/object_detection/train_FCOS.py community (archive-listed) ran · fixture could not drive it no licence file found · pointer only · 99d667302be1c9e3 · report
reduce_sum lijain/FCOS-change/fcos_core/modeling/rpn/fcos/loss.py community (archive-listed) ran · violated contract fingerprinted no licence file found · pointer only · 73567c93e91cf2f7 · report
sigmoid_focal_loss_cpu BIYTC/mobilenet_maskrcnn/maskrcnn_benchmark/layers/sigmoid_focal_loss.py community (archive-listed) ran MIT recorded; this copy not marked cleared · pointer only · c42eaa8eb1b704cd · report
smooth_l1_loss BIYTC/mobilenet_maskrcnn/maskrcnn_benchmark/layers/smooth_l1_loss.py community (archive-listed) ran MIT recorded; this copy not marked cleared · pointer only · e261fa29066b37e5 · report
LR Zanderzt/TensorRT_Mask_RCNN/demo/zyw.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 0eaf951d3a22588b · report
RF Zanderzt/TensorRT_Mask_RCNN/demo/zyw.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 00700fd67cb3e29a · report
balanced_l1_loss Iamal1/maskrcnn-benchmark/maskrcnn_benchmark/layers/balanced_l1_loss.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · cf6230491f9702dc · report
bbox_overlaps_aligned xytpai/fcos/libs/iou_loss.py community (archive-listed) unverified MIT (permissive) · 318c2c9407b81028 · report
build_roi_box_head FluteXu/ms-project/build/lib.linux-x86_64-3.7/maskrcnn_benchmark/modeling/roi_heads/box_head/box_head.py community (archive-listed) unverified MIT (permissive) · cf6c9b5f6174fc81 · report
centerness_loss srihari-humbarwadi/tensorflow_fcos/tensorflow_fcos/models/fcos/losses.py community (archive-listed) unverified Apache-2.0 (permissive) · 987c1ea87f06ee22 · report
conv1x1 ricky40403/Fcos_seg/Fcos_seg/backbone/volvenet.py community (archive-listed) unverified MIT (permissive) · 9e931093b7cb657e · report
conv3x3 ricky40403/Fcos_seg/Fcos_seg/backbone/volvenet.py community (archive-listed) unverified MIT (permissive) · 971b790fc16af272 · report
conv_block srihari-humbarwadi/tensorflow_fcos/tensorflow_fcos/models/blocks.py community (archive-listed) unverified Apache-2.0 (permissive) · 43351463fea5b39a · report
draw_boxes_cv2 srihari-humbarwadi/tensorflow_fcos/tensorflow_fcos/utils/visualization.py community (archive-listed) unverified Apache-2.0 (permissive) · f900af0f07e48e3f · report
expand_masks tuananh1007/Faster-R-CNN-and-Mask-R-CNN-in-PyTorch-1.0/maskrcnn_benchmark/modeling/roi_heads/mask_head/inference.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 762ce037e4512c48 · report
focal_loss srihari-humbarwadi/tensorflow_fcos/tensorflow_fcos/models/fcos/losses.py community (archive-listed) unverified Apache-2.0 (permissive) · fce50f2fda34fc22 · report
format_prediction_string markson14/WheatDet/demo/wheat_inference.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 069333d11241eccd · report
get_group_gn BIYTC/mobilenet_maskrcnn/maskrcnn_benchmark/modeling/make_layers.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 83c64313d0501174 · report
interpolate BIYTC/mobilenet_maskrcnn/maskrcnn_benchmark/layers/misc.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 2902bf4410253ff7 · report
iou_loss srihari-humbarwadi/tensorflow_fcos/tensorflow_fcos/models/fcos/losses.py community (archive-listed) unverified Apache-2.0 (permissive) · 5e47641ad906ae7b · report
iou_loss xytpai/fcos/libs/iou_loss.py community (archive-listed) unverified MIT (permissive) · dbd9612822534e83 · report
l2_loss Iamal1/maskrcnn-benchmark/maskrcnn_benchmark/layers/l2_loss.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 5ab322eae8b53480 · report
make_coco_detection ricky40403/Fcos_seg/Fcos_seg/core/coco_eval.py community (archive-listed) unverified MIT (permissive) · c5c7f9c741faf54d · report
project_masks_on_boxes tuananh1007/Faster-R-CNN-and-Mask-R-CNN-in-PyTorch-1.0/maskrcnn_benchmark/modeling/roi_heads/mask_head/loss.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 7282d9e488dd0a6d · report
read_custom_dict PeterTKovacs/zold137/drone_demo/custom_train.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 84fb771ac13f3af1 · report
resnet18 ricky40403/Fcos_seg/Fcos_seg/backbone/resnet.py community (archive-listed) unverified MIT (permissive) · fc9af2f2cc533781 · report
resnet18 xytpai/fcos/backbone.py community (archive-listed) unverified MIT (permissive) · 66e10ac6440feae6 · report
resnet34 xytpai/fcos/backbone.py community (archive-listed) unverified MIT (permissive) · fabaffc1a606ef9b · report
sigmoid_focal_loss_cpu Iamal1/maskrcnn-benchmark/maskrcnn_benchmark/layers/sigmoid_focal_loss.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 426fd02a2beaf826 · report
upsample_like srihari-humbarwadi/tensorflow_fcos/tensorflow_fcos/models/blocks.py community (archive-listed) unverified Apache-2.0 (permissive) · 11565a347678ccac · report
vovnet57 ricky40403/Fcos_seg/Fcos_seg/backbone/volvenet.py community (archive-listed) unverified MIT (permissive) · f9f03971f1bab8c1 · report
get_lr identical code first harvested elsewhere ran · honoured contract licence of this copy not recorded · 7337f1f5ff01dcd0 · report

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