Papers › COCO-Stuff: Thing and Stuff Classes in Context

COCO-Stuff: Thing and Stuff Classes in Context

12 Dec 2016CVPR 2018 6arXiv:1612.03716archive 2025-07-28

Holger Caesar, Jasper Uijlings, Vittorio Ferrari

Semantic classes can be either things (objects with a well-defined shape, e.g. car, person) or stuff (amorphous background regions, e.g. grass, sky). While lots of classification and detection works focus on thing classes, less attention has been given to stuff classes. Nonetheless, stuff classes are important as they allow to explain important aspects of an image, including (1) scene type; (2) which thing classes are likely to be present and their location (through contextual reasoning); (3) physical attributes, material types and geometric properties of the scene. To understand stuff and things in context we introduce COCO-Stuff, which augments all 164K images of the COCO 2017 dataset with pixel-wise annotations for 91 stuff classes. We introduce an efficient stuff annotation protocol based on superpixels, which leverages the original thing annotations. We quantify the speed versus quality trade-off of our protocol and explore the relation between annotation time and boundary complexity. Furthermore, we use COCO-Stuff to analyze: (a) the importance of stuff and thing classes in terms of their surface cover and how frequently they are mentioned in image captions; (b) the spatial relations between stuff and things, highlighting the rich contextual relations that make our dataset unique; (c) the performance of a modern semantic segmentation method on stuff and thing classes, and whether stuff is easier to segment than things.

PaperPDFConference PDFCodeCode Syntology ran

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

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

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

Code

The archive's official repository (nightrome/cocostuff) was not harvested; the 29 samples below come from 4 community repositories.

Syntology 29 code samples harvested from 4 repositories linked to this paper: 8 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; 1 where Syntology's instrument failed) · 21 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 29 samples from 4 repositories, 8 ran (7 with no instrument failure; 1 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 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

nightrome/cocostuff officialmentioned on GitHubpytorchSyntology: not harvested report
LeadingIndiaAI/COCO-DATASET-STUFF-SEGMENTATION-CHALLENGE mentioned on GitHubtfMITSyntology: not harvested report
divyanshpuri02/COCO_2018-Stuff-Segmentation-Challenge mentioned on GitHubtfMITSyntology: 23 samples, 4 ran (0 instrument-failed) · 19 unverified report
johnnylu305/deeplab-imagenet-pytorch mentioned on GitHubpytorchMITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
joykour/COCO-Dataset-2018-Stuff-Segmentation-Challenge mentioned on GitHubtfMITSyntology: not harvested report
kazuto1011/deeplab-pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
nightrome/cocostuff10k mentioned on GitHubSyntology: not harvested report
waggle-sensor/plugin-water-detector mentioned on GitHubpytorchSyntology: not harvested report
woonhahaha/place-classification mentioned on GitHubpytorchMITSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
zllrunning/deeplab-pytorch-crf mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution,... (arXiv:1606.00915; that paper's own run record: 43 ran (of which 12 constructed an object rather than computing a result; 35 with no instrument failure: 1 honoured, 0 violated, 34 with no contract checked; 8 where Syntology's instrument failed) · 20 unverified); nothing checks that they implement this paper's method. 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

29 samples harvested: 8 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; 1 where Syntology's instrument failed) · 21 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.

1ran · our draft was wrong
7ran
21unverified

Licence: 0 of the 29 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 4 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. 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.

divyanshpuri02/COCO_2018-Stuff-Segmentation-Challenge community (archive-listed) 23 samples, 4 ran (0 instrument-failed) · 19 unverified
BN COCO_2018-Stuff-Segmentation-Challenge/keras_segmentation/models/_pspnet_2.py ran MIT (permissive) · 4b7a2eb55d105ec7 · report fixture: signature name:str/0/str · returned BatchNormalization · level recorded 2026-09-26
get_iou in 34 papers COCO_2018-Stuff-Segmentation-Challenge/keras_segmentation/metrics.py ran MIT (permissive) · 3a10ab78ca4c1225 · report fixture: signature gt:ndarray/2/int, pr:ndarray/2/int, n_classes:int/0/int · returned ndarray · level recorded 2026-09-26
residual_conv COCO_2018-Stuff-Segmentation-Challenge/keras_segmentation/models/_pspnet_2.py ran MIT (permissive) · 82a0ef59dba6ebea · report fixture: signature prev:KerasTensor/0/float, level:int/0/int, pad:int/0/int, lvl:int/0/int, sub_lvl:int/0/int, modify_stride:bool/0/bool · returned KerasTensor · level recorded 2026-09-26
short_convolution_branch COCO_2018-Stuff-Segmentation-Challenge/keras_segmentation/models/_pspnet_2.py ran MIT (permissive) · 84e5f9e974dc2863 · report fixture: signature prev:KerasTensor/0/float, level:int/0/int, lvl:int/0/int, sub_lvl:int/0/int, modify_stride:bool/0/bool · returned KerasTensor · level recorded 2026-09-26
conv_block in 95 papers COCO_2018-Stuff-Segmentation-Challenge/keras_segmentation/models/resnet50.py unverified MIT (permissive) · ee7d77d25024c3a5 · report
get_mobilenet_encoder COCO_2018-Stuff-Segmentation-Challenge/keras_segmentation/models/mobilenet.py unverified MIT (permissive) · 70a0b32eb124b601 · report
get_segmentation_model COCO_2018-Stuff-Segmentation-Challenge/keras_segmentation/models/model_utils.py unverified MIT (permissive) · 1d6189bd96c34f38 · report
get_vgg_encoder COCO_2018-Stuff-Segmentation-Challenge/keras_segmentation/models/vgg16.py unverified MIT (permissive) · 115caab8fd493c77 · report
identity_block in 32 papers COCO_2018-Stuff-Segmentation-Challenge/keras_segmentation/models/resnet50.py unverified MIT (permissive) · 25234d91e4d3e193 · report
one_side_pad COCO_2018-Stuff-Segmentation-Challenge/keras_segmentation/models/resnet50.py unverified MIT (permissive) · 51603e9141ca0cfa · report
pool_block COCO_2018-Stuff-Segmentation-Challenge/keras_segmentation/models/pspnet.py unverified MIT (permissive) · f309c7837117edfe · report
pspnet COCO_2018-Stuff-Segmentation-Challenge/keras_segmentation/models/pspnet.py unverified MIT (permissive) · 8c73c0be91c13c4a · report
relu6 in 14 papers COCO_2018-Stuff-Segmentation-Challenge/keras_segmentation/models/mobilenet.py unverified MIT (permissive) · a18ef743a6887e2f · report
resize_image in 74 papers COCO_2018-Stuff-Segmentation-Challenge/keras_segmentation/models/model_utils.py unverified MIT (permissive) · e644ee2441042518 · report
segnet COCO_2018-Stuff-Segmentation-Challenge/keras_segmentation/models/segnet.py unverified MIT (permissive) · 3d468e746996569a · report
segnet_decoder COCO_2018-Stuff-Segmentation-Challenge/keras_segmentation/models/segnet.py unverified MIT (permissive) · 51df4349985bca53 · report
unet in 13 papers COCO_2018-Stuff-Segmentation-Challenge/keras_segmentation/models/unet.py unverified MIT (permissive) · 828b452ccafcf471 · report
unet_mini COCO_2018-Stuff-Segmentation-Challenge/keras_segmentation/models/unet.py unverified MIT (permissive) · a5d64b7c14a79540 · report
vanilla_encoder COCO_2018-Stuff-Segmentation-Challenge/keras_segmentation/models/basic_models.py unverified MIT (permissive) · d82d8b54685dac62 · report
vgg_pspnet COCO_2018-Stuff-Segmentation-Challenge/keras_segmentation/models/pspnet.py unverified MIT (permissive) · b09777132f95aeac · report
vgg_segnet COCO_2018-Stuff-Segmentation-Challenge/keras_segmentation/models/segnet.py unverified MIT (permissive) · 1f531434fd350936 · report
vgg_unet COCO_2018-Stuff-Segmentation-Challenge/keras_segmentation/models/unet.py unverified MIT (permissive) · a6d32a4056bf95cb · report
johnnylu305/deeplab-imagenet-pytorch community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
bytescale oldscipy/misc.py ran MIT (permissive) · 4a9f66ff9bd360ed · report fixture: signature data:ndarray/2/float, cmin:NoneType/0/?, cmax:NoneType/0/?, high:int/0/int, low:int/0/int · returned ndarray · level recorded 2026-09-26
deeplabv2_resnet101 hubconf.py ran MIT (permissive) · 915eeb627651ba7f · report fixture: signature pretrained:NoneType/0/?, n_classes:int/0/int, scales:list/1/float · returned MSC · level recorded 2026-09-26
toimage oldscipy/misc.py unverified MIT (permissive) · 7e1307c1f60e3ef3 · report
kazuto1011/deeplab-pytorch community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
translate_layer_name convert.py ran · our draft was wrong MIT (permissive) · d479911243af2856 · report fixture: signature source:str/0/str, target:str/0/str · returned str · level recorded 2026-09-22
woonhahaha/place-classification community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
get_classtable place_classification.py ran MIT (permissive) · d27dc1b55510df0a · report fixture: signature CONFIG:callable/0/? · returned dict · level recorded 2026-09-26
get_device in 101 papers place_classification.py unverified MIT (permissive) · c38aeadab512af52 · report

Tasks

Image CaptioningSemantic SegmentationSuperpixels

Datasets

Introduced by this paper, per the archive.

COCO-Stuff

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation COCO-Stuff Deeplab v2 F.W. IU 47.6 #1 of 1 Archive leaderboard report
Semantic Segmentation COCO-Stuff Deeplab v2 Per-Class Accuracy 45.1 #1 of 1 Archive leaderboard report
Semantic Segmentation COCO-Stuff Deeplab v2 Pixel Accuracy 63.6 #1 of 1 Archive leaderboard report
Semantic Segmentation COCO-Stuff Deeplab v2 mIoU 33.2 #1 of 1 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

SPEED

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