Papers › The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation

The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation

28 Nov 2016arXiv:1611.09326archive 2025-07-28

Simon Jégou, Michal Drozdzal, David Vazquez, Adriana Romero, Yoshua Bengio

State-of-the-art approaches for semantic image segmentation are built on Convolutional Neural Networks (CNNs). The typical segmentation architecture is composed of (a) a downsampling path responsible for extracting coarse semantic features, followed by (b) an upsampling path trained to recover the input image resolution at the output of the model and, optionally, (c) a post-processing module (e.g. Conditional Random Fields) to refine the model predictions. Recently, a new CNN architecture, Densely Connected Convolutional Networks (DenseNets), has shown excellent results on image classification tasks. The idea of DenseNets is based on the observation that if each layer is directly connected to every other layer in a feed-forward fashion then the network will be more accurate and easier to train. In this paper, we extend DenseNets to deal with the problem of semantic segmentation. We achieve state-of-the-art results on urban scene benchmark datasets such as CamVid and Gatech, without any further post-processing module nor pretraining. Moreover, due to smart construction of the model, our approach has much less parameters than currently published best entries for these datasets. Code to reproduce the experiments is available here : https://github.com/SimJeg/FC-DenseNet/blob/master/train.py

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

The archive's official repository (SimJeg/FC-DenseNet) was not harvested; the 24 samples below come from 5 community repositories.

Syntology 24 code samples harvested from 5 repositories linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 12 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 24 samples from 5 repositories, 12 ran (12 with no instrument failure; 0 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 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

SimJeg/FC-DenseNet officialmentioned in papermentioned on GitHubSyntology: not harvested report
0bserver07/One-Hundred-Layers-Tiramisu mentioned on GitHubtfMITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
IllIIIllll/where-is-wally mentioned on GitHubtfSyntology: not harvested report
Kaido0/Brain-Tissue-Segment-Keras mentioned on GitHubtfSyntology: not harvested report
Osdel/ssnets mentioned on GitHubtfSyntology: not harvested report
SANKHA1/Vehicle-Detection mentioned on GitHubSyntology: not harvested report
Septembit/Image-segmentation mentioned on GitHubpytorchSyntology: not harvested report
Vamshi399/CarND-Vehicle-Detection mentioned on GitHubSyntology: not harvested report
ankit-vaghela30/Cilia-Segmentation mentioned on GitHubMITSyntology: 9 samples, 6 ran (0 instrument-failed) · 3 unverified report
asprenger/keras_fc_densenet mentioned on GitHubtfSyntology: not harvested report
bfortuner/pytorch_tiramisu mentioned on GitHubpytorchSyntology: 3 samples, 0 ran · 3 unverified report
boris127/vehicle-detection mentioned on GitHubSyntology: not harvested report
datoboat/Vehicle-Detection mentioned on GitHubSyntology: 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
demul/image_segmentation_project mentioned on GitHubtfSyntology: not harvested report
kannyjyk/Nested-UNet mentioned on GitHubtfSyntology: not harvested report
koryako/AI-application mentioned on GitHubtfSyntology: not harvested report
kskim-phd/mfcn mentioned on GitHubpytorchMITSyntology: 6 samples, 4 ran (0 instrument-failed) · 2 unverified report
mrkolarik/3d-brain-segmentation mentioned on GitHubtfSyntology: not harvested report
noornk/U-Net mentioned on GitHubpytorchSyntology: not harvested report
pattyhendrix/CamVid-95-accuracy mentioned on GitHubMITSyntology: not harvested report
petko-nikolov/pysemseg mentioned on GitHubpytorchSyntology: 3 samples, 0 ran · 3 unverified report
smdYe/FC-DenseNet-Keras mentioned on GitHubSyntology: not harvested report
vivaan-park/where-is-wally mentioned on GitHubtfSyntology: 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

24 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 12 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.

12ran
12unverified

Licence: 7 of the 24 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 5 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. 3 samples whose link to this paper records no repository are 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.

0bserver07/One-Hundred-Layers-Tiramisu community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
normalized in 19 papers helper.py ran MIT (permissive) · 600dd344d089e843 · report fixture: signature rgb:ndarray/3/int · returned ndarray · level recorded 2026-09-26
one_hot_it helper.py ran MIT (permissive) · 8eb260280ed17f0f · report fixture: signature labels:ndarray/2/int, w:int/0/int, h:int/0/int · returned ndarray · level recorded 2026-09-26
load_data in 700 papers camvid_data_loader.py unverified MIT (permissive) · ee76790f2e23db5a · report
ankit-vaghela30/Cilia-Segmentation community (archive-listed) 9 samples, 6 ran (0 instrument-failed) · 3 unverified
blur in 13 papers hastings/preprocessing.py ran MIT (permissive) · 606293610ee73f36 · report fixture: signature image:ndarray/2/int, b:int/0/int · returned ndarray · level recorded 2026-09-26
gray2rgb in 10 papers hastings/preprocessing.py ran MIT (permissive) · 229fb6fceb2b565a · report fixture: signature image:ndarray/2/int · returned ndarray · level recorded 2026-09-26
load_all_video hastings/io_support.py ran MIT (permissive) · ba25286a61fa1d4f · report fixture: signature hash_file_path:str/0/str, video_parent_path:str/0/str · returned dict · level recorded 2026-09-26
load_img in 47 papers hastings/io_support.py ran MIT (permissive) · 71d2f0c11ca47487 · report fixture: signature img_parent_path:str/0/str, hash:str/0/str · returned ndarray · level recorded 2026-09-26
load_video in 20 papers hastings/io_support.py ran MIT (permissive) · 6b7485606e8ec4b4 · report fixture: signature folder:str/0/str · returned list · level recorded 2026-09-26
threshold in 9 papers hastings/preprocessing.py ran MIT (permissive) · cc07c5438fa01645 · report fixture: signature image:ndarray/2/int, t:int/0/int · returned ndarray · level recorded 2026-09-26
bn in 19 papers hastings/tiramisu_model.py unverified MIT (permissive) · 011e9d1f4a18f0c1 · report
dropout in 34 papers hastings/tiramisu_model.py unverified MIT (permissive) · f60d7b457f163df3 · report
bfortuner/pytorch_tiramisu community (archive-listed) 3 samples, 0 ran · 3 unverified
FCDenseNet103 models/tiramisu.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own unverified licence of this copy not recorded · a31003fad13ae67c · report
FCDenseNet57 models/tiramisu.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own unverified licence of this copy not recorded · f1271d09e9ba1ad7 · report
FCDenseNet67 models/tiramisu.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own unverified licence of this copy not recorded · cfa9b6051f647903 · report
kskim-phd/mfcn community (archive-listed) 6 samples, 4 ran (0 instrument-failed) · 2 unverified
center_crop in 48 papers MFCN_SMC/code_MFCN/layers.py ran fingerprinted MIT (permissive) here; the stored copy is pointer only · 9d5555c9ff725b7f · report fixture: signature layer:Tensor/4/float, max_height:int/0/int, max_width:int/0/int · returned Tensor · level recorded 2026-09-24
center_crop in 48 papers MFCN_SMC/code_MFCN/mydataset.py ran fingerprinted MIT (permissive) · 2b32f51f5f7b51cc · report fixture: signature images:Tensor/3/float · returned Tensor · level recorded 2026-09-26
center_crop_mask MFCN_SMC/code_MFCN/mydataset.py ran MIT (permissive) · 799d1ba8540920a4 · report fixture: signature images:Image/0/? · returned Image · level recorded 2026-09-26
get_JI MFCN_SMC/code_MFCN/stage1_conventional_model.py ran MIT (permissive) · f19ea4f954b9e8d0 · report fixture: signature pred_m:ndarray/2/bool, gt_m:ndarray/2/bool · returned float64 · level recorded 2026-09-26
get_JI MFCN_SMC/code_MFCN/stage2_patch_wise.py unverified MIT (permissive) · 36a022450e439192 · report
post_processing in 9 papers MFCN_SMC/code_MFCN/stage1_conventional_model.py unverified MIT (permissive) · 65d0d9510aa373d4 · report
petko-nikolov/pysemseg community (archive-listed) 3 samples, 0 ran · 3 unverified
fcdensenet103 pysemseg/models/densenet.py unverified GPL-3.0 (copyleft) · pointer only · a8205d6e6712fbf5 · report
fcdensenet56 pysemseg/models/densenet.py unverified GPL-3.0 (copyleft) · pointer only · fc05fafe6352aa0c · report
fcdensenet67 pysemseg/models/densenet.py unverified GPL-3.0 (copyleft) · pointer only · 71b9ef5924a9d9be · report

Tasks

Image SegmentationSegmentationSemantic Segmentationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation CamVid FC-DenseNet103 Global Accuracy 91.5% #12 of 21 Archive leaderboard report
Semantic Segmentation CamVid FC-DenseNet103 Mean IoU 66.9% #12 of 21 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.

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