Papers › Fully Convolutional Networks for Semantic Segmentation

Fully Convolutional Networks for Semantic Segmentation

14 Nov 2014CVPR 2015 6arXiv:1411.4038archive 2025-07-28

Jonathan Long, Evan Shelhamer, Trevor Darrell

Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, exceed the state-of-the-art in semantic segmentation. Our key insight is to build "fully convolutional" networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning. We define and detail the space of fully convolutional networks, explain their application to spatially dense prediction tasks, and draw connections to prior models. We adapt contemporary classification networks (AlexNet, the VGG net, and GoogLeNet) into fully convolutional networks and transfer their learned representations by fine-tuning to the segmentation task. We then define a novel architecture that combines semantic information from a deep, coarse layer with appearance information from a shallow, fine layer to produce accurate and detailed segmentations. Our fully convolutional network achieves state-of-the-art segmentation of PASCAL VOC (20% relative improvement to 62.2% mean IU on 2012), NYUDv2, and SIFT Flow, while inference takes one third of a second for a typical image.

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

Syntology 4 code samples harvested from 3 repositories linked to this paper: 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) · 1 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: community (archive-listed): 4 samples from 3 repositories, 3 ran (0 with no instrument failure; 3 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 7 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.

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

Anirudh0707/Roads-and-Building-Segmentation mentioned on GitHubSyntology: not harvested report
DLWK/EANet mentioned on GitHubpytorchSyntology: not harvested report
GodPater/model_fcn mentioned on GitHubtfSyntology: not harvested report
LeeMax117/FCN_8s mentioned on GitHubtfSyntology: not harvested report
LeeMax117/week10_homework mentioned on GitHubtfSyntology: not harvested report
Niloy-Chakraborty/Image_Segmentation_Model mentioned on GitHubSyntology: not harvested report
RogerQi/pascal-5i mentioned on GitHubpytorchMITSyntology: not harvested report
SDMrFeng/quiz-w10-fcn mentioned on GitHubtfSyntology: not harvested report
Segmentation-Road-Detection/Semantic-Segmentation mentioned on GitHubSyntology: not harvested report
SethEBaldwin/FCN mentioned on GitHubtfSyntology: not harvested report
SophiaYuSophiaYu/FCN_SemanticSegmentation mentioned on GitHubtfSyntology: not harvested report
TianchengQ/FCN mentioned on GitHubtfSyntology: not harvested report
YigeunLee/fcn32 mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
alvinwen428/featurecp mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Predictive Inference with Feature Conformal Prediction (arXiv:2210.00173; that paper's own run record: 0 ran · 1 unverified); nothing checks that they implement this paper's method. report
andyzeng/apc-vision-toolbox mentioned on GitHubBSD-2-ClauseSyntology: not harvested report
anoushkrit/Knowledge mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Private Machine Learning in TensorFlow using Secure Computation (arXiv:1810.08130; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
azraelzhor/tf-FCN mentioned on GitHubtfSyntology: not harvested report
colorfulxd/WK10_FCN mentioned on GitHubtfSyntology: not harvested report
demul/image_segmentation_project mentioned on GitHubtfSyntology: not harvested report
faroukmokhtar/ImageSegmentationPASCAL mentioned on GitHubSyntology: not harvested report
frank-roesler/Image_Segmentation mentioned on GitHubpytorchSyntology: not harvested report
fxfviolet/FCN_for_segmantic_segmentation mentioned on GitHubtfSyntology: not harvested report
giovanniguidi/FCN-keras mentioned on GitHubSyntology: not harvested report
githubfa/FCN mentioned on GitHubtfSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
guilhermesantos/Semantic-Image-Segmentation mentioned on GitHubpytorchSyntology: not harvested report
hahahappyboy/GANForCartoon mentioned on GitHubpytorchGPL-2.0Syntology: not harvested report
hitukensinn/quiz-w9-code mentioned on GitHubtfSyntology: not harvested report
hz-ants/apc-vision-toolbox mentioned on GitHubBSD-2-ClauseSyntology: not harvested report
inder9999/ISIC2017_skin_lesion_segmentation mentioned on GitHubpytorchSyntology: not harvested report
jqueguiner/camembert-as-a-service mentioned on GitHubpytorchMITSyntology: not harvested report
jqueguiner/image-segmentation mentioned on GitHubGPL-3.0Syntology: not harvested report
kbardool/mrcnn3 mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
koryako/AI-application mentioned on GitHubtfSyntology: not harvested report
krutikabapat/Sematic_Segmentation_Using_Pytorch mentioned on GitHubSyntology: not harvested report
lanthlove/segmentation-fcn mentioned on GitHubtfSyntology: not harvested report
martinkersner/py_img_seg_eval mentioned on GitHubSyntology: not harvested report
minoring/fcn mentioned on GitHubtfSyntology: not harvested report
muramasa8191/DeepLearning mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to U-Net: Convolutional Networks for Biomedical Image Segmentation (arXiv:1505.04597; that paper's own run record: 530 ran (of which 247 constructed an object rather than computing a result; 378 with no instrument failure: 18 honoured, 10 violated, 350 with no contract checked; 152 where Syntology's instrument failed) · 227 unverified); nothing checks that they implement this paper's method. report
pessimiss/ai100-w9-master mentioned on GitHubtfSyntology: not harvested report
pochih/fcn-pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
robromijnders/segm mentioned on GitHubtfSyntology: not harvested report
shenshutao/image_segmentation mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to U-Net: Convolutional Networks for Biomedical Image Segmentation (arXiv:1505.04597; that paper's own run record: 530 ran (of which 247 constructed an object rather than computing a result; 378 with no instrument failure: 18 honoured, 10 violated, 350 with no contract checked; 152 where Syntology's instrument failed) · 227 unverified); nothing checks that they implement this paper's method. report
sigtot/unet-auto 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
stoensin/w10-cnn-SegmentationClass mentioned on GitHubtfSyntology: not harvested report
sunnynevarekar/FCN mentioned on GitHubtfSyntology: not harvested report
tsixta/jnet 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
zhuotongchen/self-healing-robust-neural-networks-via-closed-loop-control mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation (arXiv:1511.00561; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 8 where Syntology's instrument failed) · 22 unverified); nothing checks that they implement this paper's method. report
zhuyi55/week10 mentioned on GitHubtfSyntology: not harvested report
Jackey9797/FCN mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code3 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code3 mindsporeSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

4 samples harvested: 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) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure 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 · our draft was wrong
1ran; the contract check could not run
1unverified

Licence: 4 of the 4 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 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “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.

YigeunLee/fcn32 community (archive-listed) 1 sample, 0 ran · 1 unverified
get_result in 30 papers fully_cnn.py unverified no licence file found · pointer only · 73d1eec357fb97af · report
githubfa/FCN community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
image2label convert_fcn_dataset.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · f3ca1f3716d95661 · report fixture: signature im:ndarray/3/int · returned ndarray · level recorded 2026-09-22
read_images_names convert_fcn_dataset.py ran · our draft was wrong no licence file found · pointer only · 016fff2e8cba6727 · report fixture: signature root:str/0/str, train:bool/0/bool · returned zip · level recorded 2026-09-22
pochih/fcn-pytorch community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
make_layers in 155 papers python/fcn.py ran · our draft was wrong no licence file found · pointer only · 35e373ea432491af · report fixture: signature cfg:list/1/int, batch_norm:bool/0/bool · returned Sequential · level recorded 2026-09-22

Tasks

Crack SegmentationMulti-tissue Nucleus SegmentationMultispectral Object DetectionSegmentationSemantic SegmentationThermal Image Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Crack Segmentation CrackVision12K FCN mIoU 0.59842 #3 of 4 Archive leaderboard report
Multi-tissue Nucleus Segmentation Kumar FCN8 (e) Dice 0.797 #14 of 18 Archive leaderboard report
Multi-tissue Nucleus Segmentation Kumar FCN8 (e) Hausdorff Distance (mm) 31.2 #14 of 18 Archive leaderboard report
Multispectral Object Detection KAIST Multispectral Pedestrian Detection Benchmark FusionRPN+BF All Miss Rate 51.70 #15 of 17 Archive leaderboard report
Semantic Segmentation ADE20K FCN Validation mIoU 29.39 #229 of 235 Archive leaderboard report
Semantic Segmentation COCO-Stuff test FCN (VGG-16) mIoU 22.7% #21 of 21 Archive leaderboard report
Semantic Segmentation Event-based Segmentation Dataset FCN mIoU 59.6 #6 of 6 Archive leaderboard report
Semantic Segmentation Fine-Grained Grass Segmentation Dataset FCN mIoU 47.47 #9 of 10 Archive leaderboard report
Semantic Segmentation PASCAL Context FCN-8s mIoU 37.8 #63 of 66 Archive leaderboard report
Semantic Segmentation PASCAL VOC 2012 test FCN (VGG-16) Mean IoU 62.2% #49 of 51 Archive leaderboard report
Semantic Segmentation SELMA FCN mIoU 68.2 #6 of 7 Archive leaderboard report
Semantic Segmentation SkyScapes-Dense FCN8s (ResNet-50) Mean IoU 33.06 #3 of 7 Archive leaderboard report
Semantic Segmentation SkyScapes-Lane FCN8s (ResNet-50) Mean IoU 13.74 #2 of 2 Archive leaderboard report
Semantic Segmentation Trans10K FCN GFLOPs 42.23 #11 of 15 Archive leaderboard report
Semantic Segmentation Trans10K FCN mIoU 62.75% #11 of 15 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

Average PoolingConvolutionDense ConnectionsDropoutGlobal Average PoolingMax PoolingReLUSoftmax

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