Papers › Unified Perceptual Parsing for Scene Understanding

Unified Perceptual Parsing for Scene Understanding

26 Jul 2018ECCV 2018 9arXiv:1807.10221archive 2025-07-28

Tete Xiao, Yingcheng Liu, Bolei Zhou, Yuning Jiang, Jian Sun

Humans recognize the visual world at multiple levels: we effortlessly categorize scenes and detect objects inside, while also identifying the textures and surfaces of the objects along with their different compositional parts. In this paper, we study a new task called Unified Perceptual Parsing, which requires the machine vision systems to recognize as many visual concepts as possible from a given image. A multi-task framework called UPerNet and a training strategy are developed to learn from heterogeneous image annotations. We benchmark our framework on Unified Perceptual Parsing and show that it is able to effectively segment a wide range of concepts from images. The trained networks are further applied to discover visual knowledge in natural scenes. Models are available at \url{https://github.com/CSAILVision/unifiedparsing}.

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="1807.10221")

Code

Syntology Ran 9 of 28 code samples harvested from 4 repositories linked to this paper; 19 have no recorded run. Of those that ran: 1 ran · honoured contract; 6 ran · our draft was wrong; 1 ran · fixture could not drive it; 1 ran with no contract checked.

By repository: community (archive-listed): 28 samples from 4 repositories, 9 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

CSAILVision/unifiedparsing officialmentioned in papermentioned on GitHubpytorchMIT report
163GitHub/AI mentioned on GitHubpytorch report
CSAILVision/semantic-segmentation-pytorch mentioned on GitHubpytorchBSD-3-Clause report
ESA-PhiLab/PhilEO-MajorTOM mentioned on GitHubpytorchApache-2.0 report
Rosie-Brigham/sesmeg mentioned on GitHubpytorch report
Shun14/UperNet mentioned on GitHubpaddleApache-2.0 report
SonpKing/semantic-segmentation-pytorch mentioned on GitHubpytorchMIT report
cameronthurston/CSAILVisionUpdated mentioned on GitHubpytorch report
dingmyu/davit mentioned on GitHubpytorch report
fenglian425/Agriculture_AI mentioned on GitHubpytorch report
kdhingra307/temp mentioned on GitHubpytorch report
keyEpoch/semen_seg-kd mentioned on GitHubpytorch report
kukby/Mish-semantic-segmentation-pytorch mentioned on GitHubpytorchBSD-3-Clause report
mdt48/semantic-segmentation-pytorch mentioned on GitHubpytorchBSD-3-Clause report
sithu31296/semantic-segmentation mentioned on GitHubpytorch report
starkgines/PDI mentioned on GitHubpytorchBSD-3-Clause report
tejaswigowda/semseg-pytorch mentioned on GitHubpytorchBSD-3-Clause report
MS-P3/code7 mindspore report
open-mmlab/mmsegmentation pytorchApache-2.0 report
pwc-1/Paper-9 mindspore 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

28 samples harvested; 9 ran; 1 honoured the contract we drafted; 19 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.

1ran · honoured contract
6ran · our draft was wrong
1ran · fixture could not drive it
1ran
19unverified

Licence: 0 of the 28 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; each sample names its own and says which. “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.

accuracy SonpKing/semantic-segmentation-pytorch/utils.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 2e932a495b2ab693 · report
channel_shuffle SonpKing/semantic-segmentation-pytorch/models/shufflenetv2.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · b9da06d4f527dd6c · report
conv3x3 SonpKing/semantic-segmentation-pytorch/models/resnet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · fac5364e2f53c6db · report
conv3x3 SonpKing/semantic-segmentation-pytorch/models/models.py community (archive-listed) ran · our draft was wrong MIT (permissive) · dbcb53696bc43ef9 · report
conv_1x1_bn SonpKing/semantic-segmentation-pytorch/models/shufflenetv2.py community (archive-listed) ran MIT (permissive) · 7765583b9e540679 · report
conv_bn SonpKing/semantic-segmentation-pytorch/models/shufflenetv2.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 2f7853ff01cbbc29 · report
get_1d_sincos_pos_embed_from_grid ESA-PhiLab/PhilEO-MajorTOM/model/phileo_vit.py community (archive-listed) ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · 4bdd36eab04c3f62 · report
get_test_config Shun14/UperNet/val.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · 20eb3e6b0aba73e4 · report
partition_list Shun14/UperNet/paddleseg/core/predict.py community (archive-listed) ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 2f75a098ce9f7b0e · report
as_numpy SonpKing/semantic-segmentation-pytorch/lib/utils/th.py community (archive-listed) unverified MIT (permissive) · c08e7121f699a983 · report
as_variable SonpKing/semantic-segmentation-pytorch/lib/utils/th.py community (archive-listed) unverified MIT (permissive) · 10bb6a2d70d61ca6 · report
colorEncode SonpKing/semantic-segmentation-pytorch/utils.py community (archive-listed) unverified MIT (permissive) · 84f0eba9ce9b82f0 · report
find_recursive starkgines/PDI/mit_semseg/utils.py community (archive-listed) unverified BSD-3-Clause (permissive) · 6890565633b480b8 · report
flip_combination Shun14/UperNet/paddleseg/core/infer.py community (archive-listed) unverified Apache-2.0 (permissive) · 95bccf5957a196e4 · report
get_2d_sincos_pos_embed ESA-PhiLab/PhilEO-MajorTOM/model/phileo_vit.py community (archive-listed) unverified Apache-2.0 (permissive) · 9417ae492629cf06 · report
get_2d_sincos_pos_embed_from_grid ESA-PhiLab/PhilEO-MajorTOM/model/phileo_vit.py community (archive-listed) unverified Apache-2.0 (permissive) · 4fd80de79832745d · report
get_core_decoder_kwargs ESA-PhiLab/PhilEO-MajorTOM/phileo-bench/models/model_AutoEncoderViTPretrained.py community (archive-listed) unverified Apache-2.0 (permissive) · 102a08ac9375eb5f · report
get_image_list Shun14/UperNet/predict.py community (archive-listed) unverified Apache-2.0 (permissive) · c8f710d7401e0006 · report
get_reverse_list Shun14/UperNet/paddleseg/core/infer.py community (archive-listed) unverified Apache-2.0 (permissive) · 026fee631ce4a66c · report
get_test_config Shun14/UperNet/predict.py community (archive-listed) unverified Apache-2.0 (permissive) · 32d2a7cc8725e25e · report
imresize starkgines/PDI/mit_semseg/dataset.py community (archive-listed) unverified BSD-3-Clause (permissive) · e23968c493407287 · report
load_url starkgines/PDI/mit_semseg/models/utils.py community (archive-listed) unverified BSD-3-Clause (permissive) · d087e320591e6ba7 · report
load_url SonpKing/semantic-segmentation-pytorch/models/resnext.py community (archive-listed) unverified MIT (permissive) · a42beb0aba2deb89 · report
mark_volatile SonpKing/semantic-segmentation-pytorch/lib/utils/th.py community (archive-listed) unverified MIT (permissive) · 32f45cf75891bd16 · report
patch_replication_callback SonpKing/semantic-segmentation-pytorch/lib/nn/modules/replicate.py community (archive-listed) unverified MIT (permissive) · 27e207fe8a74c3e7 · report
round2nearest_multiple SonpKing/semantic-segmentation-pytorch/dataset.py community (archive-listed) unverified MIT (permissive) · cc83fb3836123035 · report
setup_logger starkgines/PDI/mit_semseg/utils.py community (archive-listed) unverified BSD-3-Clause (permissive) · b50608a902a34b99 · report
unique SonpKing/semantic-segmentation-pytorch/utils.py community (archive-listed) unverified MIT (permissive) · 5feabe579b35978a · report

Tasks

2D Semantic SegmentationScene UnderstandingSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
2D Semantic Segmentation WildScenes UPerNet (ConvNeXt-L) mIoU 47.30 #2 of 5 Archive leaderboard report
Semantic Segmentation ADE20K UperNet (ResNet-101) Validation mIoU 42.66 #215 of 235 Archive leaderboard report
Semantic Segmentation ADE20K val UperNet (ResNet-101) mIoU 42.66 #93 of 95 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