Papers › Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation

Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation

24 Sep 2019ECCV 2020 8arXiv:1909.11065archive 2025-07-28

Yuhui Yuan, Xiaokang Chen, Xilin Chen, Jingdong Wang

In this paper, we address the semantic segmentation problem with a focus on the context aggregation strategy. Our motivation is that the label of a pixel is the category of the object that the pixel belongs to. We present a simple yet effective approach, object-contextual representations, characterizing a pixel by exploiting the representation of the corresponding object class. First, we learn object regions under the supervision of ground-truth segmentation. Second, we compute the object region representation by aggregating the representations of the pixels lying in the object region. Last, % the representation similarity we compute the relation between each pixel and each object region and augment the representation of each pixel with the object-contextual representation which is a weighted aggregation of all the object region representations according to their relations with the pixel. We empirically demonstrate that the proposed approach achieves competitive performance on various challenging semantic segmentation benchmarks: Cityscapes, ADE20K, LIP, PASCAL-Context, and COCO-Stuff. Cityscapes, ADE20K, LIP, PASCAL-Context, and COCO-Stuff. Our submission "HRNet + OCR + SegFix" achieves 1-st place on the Cityscapes leaderboard by the time of submission. Code is available at: https://git.io/openseg and https://git.io/HRNet.OCR. We rephrase the object-contextual representation scheme using the Transformer encoder-decoder framework. The details are presented in Section3.3.

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 9 code samples harvested from 4 repositories linked to this paper: 5 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; 4 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 8 samples from 3 repositories, 4 ran (1 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 5 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 5 samples that ran has no recorded date.

HRNet/HRNet-Semantic-Segmentation officialmentioned on GitHubpytorchNOASSERTIONSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
Burf/HRNetV2-OCR-Tensorflow2 mentioned on GitHubtfMITSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
JanMarcelKezmann/TensorFlow-Advanced-Segmentation-Models mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to 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); nothing checks that they implement this paper's method. report
openseg-group/openseg.pytorch mentioned on GitHubpytorchSyntology: 3 samples, 1 ran (1 instrument-failed) · 2 unverified report
rosinality/ocr-pytorch mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified 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
MindSpore-paper-code-3/code9 mindsporeSyntology: not harvested report
PaddlePaddle/PaddleSeg paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EdgeFlow: Achieving Practical Interactive Segmentation with Edge-Guided Flow (arXiv:2109.09406; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
kingcong/OCRNet mindsporenot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested 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/mmsegmentation pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Perceptual Artifacts Localization for Image Synthesis Tasks (arXiv:2310.05590; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 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

9 samples harvested: 5 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; 4 where Syntology's instrument failed) · 4 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.

4ran · our draft was wrong
1ran
4unverified

Licence: 1 of the 9 samples is 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.

HRNet/HRNet-Semantic-Segmentation official repository 1 sample, 1 ran (1 instrument-failed) · 0 unverified
conv3x3 in 1,376 papers lib/models/seg_hrnet.py ran · our draft was wrong no licence file found · pointer only · fac5364e2f53c6db · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
Burf/HRNetV2-OCR-Tensorflow2 community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
hr_transition_block hrnet/hrnet.py ran MIT (permissive) · 05831920f7a920c9 · report fixture: signature x:list/1/EagerTensor, n_feature:int/0/int, kwargs:dict/0/? · returned list · level recorded 2026-09-24
hr_basic_block hrnet/hrnet.py unverified MIT (permissive) · 6b491db5a0440458 · report
hr_bottleneck_block hrnet/hrnet.py unverified MIT (permissive) · be1dcef7d7100993 · report
openseg-group/openseg.pytorch community (archive-listed) 3 samples, 1 ran (1 instrument-failed) · 2 unverified
generateInstanceStats lib/metrics/cityscapes/evaluation/evalPixelLevelSemanticLabeling.py ran · our draft was wrong MIT (permissive) · 7d4554a0bd6eb4d2 · report fixture: returned dict · level recorded 2026-09-22
generateMatrix lib/metrics/cityscapes/evaluation/evalPixelLevelSemanticLabeling.py unverified MIT (permissive) · 83f120a07b1755b4 · report
getPrediction lib/metrics/cityscapes/evaluation/evalPixelLevelSemanticLabeling.py unverified MIT (permissive) · a9c50973bbd521dc · report
rosinality/ocr-pytorch community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
conv1d in 31 papers model.py ran · our draft was wrong MIT (permissive) · ab8dda773f3d5789 · report fixture: signature in_channel:int/0/int, out_channel:int/0/int · returned Sequential · level recorded 2026-09-22
conv2d in 119 papers model.py ran · our draft was wrong MIT (permissive) · 9333dd68e11e060d · report fixture: signature in_channel:int/0/int, out_channel:int/0/int, kernel_size:int/0/int · returned Sequential · level recorded 2026-09-22

Tasks

DecoderObjectSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation ADE20K HRNetV2 + OCR + RMI (PaddleClas pretrained) Validation mIoU 47.98 #155 of 235 Archive leaderboard report
Semantic Segmentation ADE20K OCR(HRNetV2-W48) Validation mIoU 45.66 #187 of 235 Archive leaderboard report
Semantic Segmentation ADE20K OCR (ResNet-101) Validation mIoU 45.28 #193 of 235 Archive leaderboard report
Semantic Segmentation ADE20K val HRNetV2 + OCR + RMI (PaddleClas pretrained) mIoU 47.98 #63 of 95 Archive leaderboard report
Semantic Segmentation ADE20K val OCR (HRNetV2-W48) mIoU 45.66 #79 of 95 Archive leaderboard report
Semantic Segmentation ADE20K val OCR (ResNet-101) mIoU 45.28 #81 of 95 Archive leaderboard report
Semantic Segmentation BDD100K val OCRNet mIoU 60.1 #8 of 24 Archive leaderboard report
Semantic Segmentation COCO-Stuff test HRNetV2 + OCR + RMI (PaddleClas pretrained) mIoU 45.2% #9 of 21 Archive leaderboard report
Semantic Segmentation COCO-Stuff test OCR (HRNetV2-W48) mIoU 40.5% #12 of 21 Archive leaderboard report
Semantic Segmentation COCO-Stuff test OCR (ResNet-101) mIoU 39.5% #16 of 21 Archive leaderboard report
Semantic Segmentation Cityscapes test HRNetV2 + OCR + Mean IoU (class) 84.5% #9 of 105 Archive leaderboard report
Semantic Segmentation Cityscapes test HRNetV2 + OCR (w/ ASP) Mean IoU (class) 83.7% #12 of 105 Archive leaderboard report
Semantic Segmentation Cityscapes test OCR (HRNetV2-W48, coarse) Mean IoU (class) 83.0% #20 of 105 Archive leaderboard report
Semantic Segmentation Cityscapes test OCR (ResNet-101, coarse) Mean IoU (class) 82.4% #27 of 105 Archive leaderboard report
Semantic Segmentation Cityscapes test OCR (ResNet-101) Mean IoU (class) 81.8% #34 of 105 Archive leaderboard report
Semantic Segmentation Cityscapes val HRNetV2 + OCR + RMI (PaddleClas pretrained) mIoU 83.6 #23 of 99 Archive leaderboard report
Semantic Segmentation Cityscapes val OCR (ResNet-101-FCN) mIoU 80.6 #48 of 99 Archive leaderboard report
Semantic Segmentation LIP val HRNetV2 + OCR + RMI (PaddleClas pretrained) mIoU 58.2% #5 of 13 Archive leaderboard report
Semantic Segmentation LIP val OCR (HRNetV2-W48) mIoU 56.65% #6 of 13 Archive leaderboard report
Semantic Segmentation LIP val OCR (ResNet-101) mIoU 55.6% #8 of 13 Archive leaderboard report
Semantic Segmentation PASCAL Context HRNetV2 + OCR + RMI (PaddleClas pretrained) mIoU 59.6 #15 of 66 Archive leaderboard report
Semantic Segmentation PASCAL Context OCR (HRNetV2-W48) mIoU 56.2 #24 of 66 Archive leaderboard report
Semantic Segmentation PASCAL Context OCR (ResNet-101) mIoU 54.8 #33 of 66 Archive leaderboard report
Semantic Segmentation PASCAL VOC 2012 test OCR (HRNetV2-W48) Mean IoU 84.5% #12 of 51 Archive leaderboard report
Semantic Segmentation PASCAL VOC 2012 test OCR (ResNet-101) Mean IoU 84.3% #13 of 51 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

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

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