Papers › Pyramid Scene Parsing Network

Pyramid Scene Parsing Network

4 Dec 2016CVPR 2017 7arXiv:1612.01105archive 2025-07-28

Hengshuang Zhao, Jianping Shi, Xiaojuan Qi, Xiaogang Wang, Jiaya Jia

Scene parsing is challenging for unrestricted open vocabulary and diverse scenes. In this paper, we exploit the capability of global context information by different-region-based context aggregation through our pyramid pooling module together with the proposed pyramid scene parsing network (PSPNet). Our global prior representation is effective to produce good quality results on the scene parsing task, while PSPNet provides a superior framework for pixel-level prediction tasks. The proposed approach achieves state-of-the-art performance on various datasets. It came first in ImageNet scene parsing challenge 2016, PASCAL VOC 2012 benchmark and Cityscapes benchmark. A single PSPNet yields new record of mIoU accuracy 85.4% on PASCAL VOC 2012 and accuracy 80.2% on Cityscapes.

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 (hszhao/PSPNet) was not harvested; the 29 samples below come from 9 community repositories.

Syntology 29 code samples harvested from 9 repositories linked to this paper: 21 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 7 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 29 samples from 9 repositories, 21 ran (14 with no instrument failure; 7 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 17 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. 1 of the 21 samples that ran has no recorded date.

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

hszhao/PSPNet officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
163GitHub/AI mentioned on GitHubpytorchSyntology: not harvested report
2023-MindSpore-1/ms-code-46 mentioned on GitHubmindsporeSyntology: not harvested report
AnirudhAchal/Human-Parsing mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
BOBrown/deeparsing-master mentioned on GitHubNOASSERTIONSyntology: not harvested report
CSAILVision/semantic-segmentation-pytorch mentioned on GitHubpytorchBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep High-Resolution Representation Learning for Visual Recognition (arXiv:1908.07919; that paper's own run record: 21 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 1 violated, 15 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified); nothing checks that they implement this paper's method. report
DiMarzioRock7/Aerial-Semantic-Segmentation-Drone mentioned on GitHubpytorchSyntology: not harvested report
DiMarzioRock7/PSPNet mentioned on GitHubpytorchSyntology: not harvested report
DoTung-bkhn/multiclass-segmentation mentioned on GitHubtfSyntology: not harvested report
EvaBr/AnatomyNets mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified report
HenonBamboo/PSPNet-MindSpore mentioned on GitHubmindsporeNOASSERTIONSyntology: not harvested 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
Lxrd-AJ/Advanced_ML 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
Mind23-2/MindCode-63 mentioned on GitHubmindsporeSyntology: not harvested report
PRBonn/bonnet mentioned on GitHubtfGPL-3.0Syntology: not harvested report
PhanTom2003/PSPnet mentioned on GitHubpytorchSyntology: not harvested report
Rintarooo/PSPNet mentioned on GitHubpytorchSyntology: not harvested report
RituYadav92/Image-segmentation mentioned on GitHubpytorchSyntology: not harvested report
Rosie-Brigham/sesmeg mentioned on GitHubpytorchSyntology: not harvested report
UBC-CIC/COVID19-L3-Net mentioned on GitHubpytorchApache-2.0Syntology: 8 samples, 7 ran (0 instrument-failed) · 1 unverified report
YininKorea/Contour-aware-equipotential-learning mentioned on GitHubpytorchMITSyntology: 7 samples, 5 ran (0 instrument-failed) · 2 unverified report
ZFTurbo/segmentation_models_3D mentioned on GitHubtfSyntology: not harvested report
branislavhesko/segmentation_framework 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
burakalperen/Pytorch-Semantic-Segmentation 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
cioppaanthony/rt-sbs mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
cj-mclaughlin/segmentation_research mentioned on GitHubtfSyntology: not harvested report
daveboat/spp mentioned on GitHubpytorchSyntology: not harvested report
fenglian425/Agriculture_AI mentioned on GitHubpytorchSyntology: not harvested report
geekswaroop/Human-Parsing mentioned on GitHubpytorchSyntology: not harvested report
holyseven/PSPNet-TF-Reproduce mentioned on GitHubtfSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
intelligent-vehicles/bevdriver mentioned on GitHubpytorchSyntology: not harvested report
irfanICMLL/structure_knowledge_distillation mentioned on GitHubpytorchBSD-2-ClauseSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
jqueguiner/camembert-as-a-service mentioned on GitHubpytorchMITSyntology: not harvested report
jqueguiner/image-segmentation mentioned on GitHubGPL-3.0Syntology: not harvested report
kannyjyk/Nested-UNet mentioned on GitHubtfSyntology: not harvested report
kazuto1011/pspnet-pytorch mentioned on GitHubpytorchMITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
kdhingra307/temp mentioned on GitHubpytorchSyntology: not harvested report
kingcong/PSPNet mentioned on GitHubmindsporenot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report
kukby/Mish-semantic-segmentation-pytorch mentioned on GitHubpytorchBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to High-Resolution Representations for Labeling Pixels and Regions (arXiv:1904.04514; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
leemathew1998/GradientWeight mentioned on GitHubpytorchSyntology: not harvested report
leemathew1998/RG mentioned on GitHubpytorchSyntology: not harvested report
manideep2510/eye-in-the-sky 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
mattangus/fast-semantic-segmentation mentioned on GitHubtfSyntology: not harvested report
mdt48/semantic-segmentation-pytorch mentioned on GitHubpytorchBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to High-Resolution Representations for Labeling Pixels and Regions (arXiv:1904.04514; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
oandrienko/fast-semantic-segmentation mentioned on GitHubtfSyntology: not harvested report
osmr/imgclsmob mentioned on GitHubmxnetMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ResNeSt: Split-Attention Networks (arXiv:2004.08955; that paper's own run record: 28 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 7 where Syntology's instrument failed) · 20 unverified); nothing checks that they implement this paper's method. report
qubvel/segmentation_models mentioned on GitHubtfSyntology: 3 samples, 1 ran (1 instrument-failed) · 2 unverified report
switchablenorms/SwitchNorm_Segmentation 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
tejaswigowda/semseg-pytorch mentioned on GitHubpytorchBSD-3-ClauseSyntology: not harvested report
tensorflow/models mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), 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), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
tensorflow/models mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), 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), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
udacity/MLND-CN-Capstone-TGSImage mentioned on GitHubSyntology: not harvested report
warmspringwinds/pytorch-segmentation-detection 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
yangyucheng000/PSPNet mentioned on GitHubmindsporeSyntology: not harvested report
2023-MindSpore-1/ms-code-215 mindsporeSyntology: not harvested report
Asthestarsfalll/PSPNet-MegEngine pytorchSyntology: not harvested report
Burf/tfdetection tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (arXiv:1506.01497; that paper's own run record: 79 ran (of which 9 constructed an object rather than computing a result; 47 with no instrument failure: 18 honoured, 5 violated, 24 with no contract checked; 32 where Syntology's instrument failed) · 45 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified), 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) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
MS-Mind/MS-Code-06 mindsporeSyntology: not harvested report
Media-Smart/vedaseg pytorchSyntology: 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) and 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
Mind23-2/MindCode-5 mindsporeSyntology: not harvested report
MindSpore-paper-code-2/code2 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
code-implementation1/Code6 mindsporeSyntology: not harvested report
divamgupta/image-segmentation-keras tfSyntology: 1 sample, 0 ran · 1 unverified 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
y-ouali/pytorch_segmentation pytorchSyntology: 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

29 samples harvested: 21 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 7 where Syntology's instrument failed) · 8 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.

7ran · our draft was wrong
14ran
8unverified

Licence: 5 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 9 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. 1 sample whose link to this paper records no repository is 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.

AnirudhAchal/Human-Parsing community (archive-listed) 1 sample, 0 ran · 1 unverified
show_image in 6 papers inference.py unverified no licence file found · pointer only · 3ac84d37ba5ffd7e · report
EvaBr/AnatomyNets community (archive-listed) 3 samples, 3 ran (3 instrument-failed) · 0 unverified
convBatch Networks.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 21482360322a0d6b · report fixture: signature nin:int/0/int, nout:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding:int/0/int, bias:bool/0/bool, layer:callable/0/?, dilation:int/0/int · returned Sequential · level recorded 2026-09-22
resnet18 in 432 papers Networks.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 8837b79c8dc51ef5 · report fixture: signature pretrained:bool/0/bool · returned DilatedResNet · level recorded 2026-09-22
upSampleConv Networks.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 5a732a32da22a9f8 · report fixture: signature nin:int/0/int, nout:int/0/int, kernel_size:int/0/int, upscale:int/0/int, padding:int/0/int, bias:bool/0/bool · returned Sequential · level recorded 2026-09-22
UBC-CIC/COVID19-L3-Net community (archive-listed) 8 samples, 7 ran (0 instrument-failed) · 1 unverified
collate_fn in 500 papers src/utils.py ran Apache-2.0 (permissive) · e0e9176fd296b349 · report fixture: signature batch:list/1/dict · returned dict · level recorded 2026-09-26
confusion_binary_class src/models/metrics.py ran Apache-2.0 (permissive) · 2238b35660ae3fe6 · report fixture: signature prediction:Tensor/1/float, truth:Tensor/1/float · returned ndarray · level recorded 2026-09-26
dice_loss in 193 papers
census: 10 implementations from 16 papers, 7 distinct outputs across 4 buckets, one shared input per bucket
src/models/losses/dice_loss.py ran fingerprinted Apache-2.0 (permissive) · da71c123fd8dd8ef · report fixture: signature probs:Tensor/2/float, target:Tensor/2/float · returned Tensor · level recorded 2026-09-26
get_class_map src/datasets/transformers/trans_utils.py ran fingerprinted Apache-2.0 (permissive) · 949969de06e73c86 · report fixture: signature n_classes:int/0/int · returned dict · level recorded 2026-09-26
get_normalization_stats src/datasets/transformers/trans_utils.py ran Apache-2.0 (permissive) · 3025e0d1d479d074 · report fixture: signature windows:list/1/str · returned tuple · level recorded 2026-09-26
get_thresholds_stats src/datasets/transformers/trans_utils.py ran fingerprinted Apache-2.0 (permissive) · 1d7510d9f3569585 · report fixture: signature windows:list/1/str · returned tuple · level recorded 2026-09-26
match_image_size src/models/semseg.py ran fingerprinted Apache-2.0 (permissive) · c8f9dfe64cb830a8 · report fixture: signature images:Tensor/4/float, logits:Tensor/4/float · returned Tensor · level recorded 2026-09-26
confusion_multi_class src/models/metrics.py unverified Apache-2.0 (permissive) · 8a4c5a21de40bb0f · report
YininKorea/Contour-aware-equipotential-learning community (archive-listed) 7 samples, 5 ran (0 instrument-failed) · 2 unverified
Get_Segmetrics utils/Evaluator.py ran MIT (permissive) · 3d0961373635b158 · report fixture: signature output:Tensor/3/int, target:Tensor/3/int, num_class:int/0/int · returned list · level recorded 2026-09-26
batch_intersection_union in 10 papers utils/Evaluator.py ran MIT (permissive) · a593c508c5bef220 · report fixture: signature predict:Tensor/2/int, target:Tensor/2/int, num_class:int/0/int, labeled:Tensor/2/int · returned tuple · level recorded 2026-09-26
batch_pix_accuracy in 12 papers utils/Evaluator.py ran MIT (permissive) · 7b9464d81818921d · report fixture: signature predict:Tensor/2/int, target:Tensor/2/int, labeled:Tensor/2/int · returned tuple · level recorded 2026-09-26
get_voc_palette utils/palette.py ran fingerprinted MIT (permissive) · d46e561fba210e1a · report fixture: signature num_classes:int/0/int · returned list · level recorded 2026-09-25
get_weights in 34 papers utils/loss.py ran MIT (permissive) · efb328cb1558491d · report fixture: signature target:Tensor/1/int · returned Tensor · level recorded 2026-09-26
convert_model in 14 papers Networks/sync_batchnorm/batchnorm.py unverified MIT (permissive) · 21d32f46755ba0dc · report
patch_replication_callback in 18 papers Networks/sync_batchnorm/replicate.py unverified MIT (permissive) · 27e207fe8a74c3e7 · report
holyseven/PSPNet-TF-Reproduce community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
coloring_image_create predict.py ran · our draft was wrong fingerprinted MIT (permissive) · 977995a57dc87d8a · report fixture: signature image_filename:str/0/str · returned str · level recorded 2026-09-22
prediction_image_create predict.py ran · our draft was wrong fingerprinted MIT (permissive) · a1fe1d6979c55a18 · report fixture: signature image_filename:str/0/str, key_word:str/0/str · returned str · level recorded 2026-09-22
irfanICMLL/structure_knowledge_distillation community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
conv3x3 in 1,376 papers networks/pspnet_combine.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · 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
kazuto1011/pspnet-pytorch community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
make_dot in 11 papers draw_model.py ran MIT (permissive) · ca6ae0c751805e86 · report fixture: signature var:Tensor/0/float, params:dict/0/? · returned Digraph · level recorded 2026-09-26
scores in 12 papers libs/utils/metric.py ran MIT (permissive) · a83c73332fef7d86 · report fixture: signature label_trues:list/1/ndarray, label_preds:list/1/ndarray, n_class:int/0/int · returned tuple · level recorded 2026-09-26
translate_layer_name convert.py unverified MIT (permissive) · 46f1b5319b0c05f8 · report
qubvel/segmentation_models community (archive-listed) 3 samples, 1 ran (1 instrument-failed) · 2 unverified
Conv1x1BnReLU segmentation_models/models/pspnet.py ran · our draft was wrong MIT (permissive) · 6967c6e3ddb59aa2 · report fixture: returned function · level recorded 2026-09-22
SpatialContextBlock segmentation_models/models/pspnet.py unverified MIT (permissive) · 68c9339a3d579243 · report
build_psp segmentation_models/models/pspnet.py unverified MIT (permissive) · 4f0550053f2e1bda · report
divamgupta/image-segmentation-keras community (archive-listed) 1 sample, 0 ran · 1 unverified
model_from_checkpoint_path keras_segmentation/pretrained.py unverified MIT (permissive) · 89798b68c1238a8d · report

Tasks

Dichotomous Image SegmentationImage ClassificationLesion SegmentationReal-Time Semantic SegmentationScene ParsingSemantic SegmentationThermal Image SegmentationVideo Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Dichotomous Image Segmentation DIS-TE1 PSPNet E-measure 0.791 #14 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 PSPNet HCE 267 #14 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 PSPNet MAE 0.089 #14 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 PSPNet S-Measure 0.725 #14 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 PSPNet max F-Measure 0.645 #14 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 PSPNet weighted F-measure 0.557 #14 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 PSPNet E-measure 0.828 #12 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 PSPNet HCE 586 #12 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 PSPNet MAE 0.092 #12 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 PSPNet S-Measure 0.763 #12 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 PSPNet max F-Measure 0.724 #12 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 PSPNet weighted F-measure 0.636 #12 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 PSPNet E-measure 0.843 #15 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 PSPNet HCE 1111 #15 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 PSPNet MAE 0.092 #15 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 PSPNet S-Measure 0.774 #15 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 PSPNet max F-Measure 0.747 #15 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 PSPNet weighted F-measure 0.657 #15 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 PSPNet E-measure 0.815 #17 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 PSPNet HCE 3806 #17 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 PSPNet MAE 0.107 #17 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 PSPNet S-Measure 0.758 #17 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 PSPNet max F-Measure 0.725 #17 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 PSPNet weighted F-measure 0.630 #17 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD PSPNet E-measure 0.802 #18 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD PSPNet HCE 1588 #18 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD PSPNet MAE 0.102 #18 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD PSPNet S-Measure 0.744 #18 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD PSPNet max F-Measure 0.691 #18 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD PSPNet weighted F-measure 0.603 #18 of 24 Archive leaderboard report
Lesion Segmentation Anatomical Tracings of Lesions After Stroke (ATLAS) PSPNet Dice 0.3571 #5 of 5 Archive leaderboard report
Lesion Segmentation Anatomical Tracings of Lesions After Stroke (ATLAS) PSPNet IoU 0.254 #5 of 5 Archive leaderboard report
Lesion Segmentation Anatomical Tracings of Lesions After Stroke (ATLAS) PSPNet Precision 0.4769 #5 of 5 Archive leaderboard report
Lesion Segmentation Anatomical Tracings of Lesions After Stroke (ATLAS) PSPNet Recall 0.3335 #5 of 5 Archive leaderboard report
Real-Time Semantic Segmentation CamVid PSPNet Frame (fps) 5.4 #29 of 29 Archive leaderboard report
Real-Time Semantic Segmentation CamVid PSPNet Time (ms) 185.0 #29 of 29 Archive leaderboard report
Real-Time Semantic Segmentation NYU Depth v2 PSPNet101 Speed(ms/f) 72 #5 of 10 Archive leaderboard report
Real-Time Semantic Segmentation NYU Depth v2 PSPNet101 mIoU 43.2 #5 of 10 Archive leaderboard report
Real-Time Semantic Segmentation NYU Depth v2 PSPNet50 Speed(ms/f) 47 #7 of 10 Archive leaderboard report
Real-Time Semantic Segmentation NYU Depth v2 PSPNet50 mIoU 41.8 #7 of 10 Archive leaderboard report
Real-Time Semantic Segmentation NYU Depth v2 PSPNet18 Speed(ms/f) 19 #10 of 10 Archive leaderboard report
Real-Time Semantic Segmentation NYU Depth v2 PSPNet18 mIoU 35.9 #10 of 10 Archive leaderboard report
Semantic Segmentation ADE20K PSPNet Test Score 55.38 #197 of 235 Archive leaderboard report
Semantic Segmentation ADE20K PSPNet Validation mIoU 44.94 #197 of 235 Archive leaderboard report
Semantic Segmentation ADE20K PSPNet (ResNet-152) Validation mIoU 43.51 #208 of 235 Archive leaderboard report
Semantic Segmentation ADE20K PSPNet (ResNet-101) Validation mIoU 43.29 #209 of 235 Archive leaderboard report
Semantic Segmentation ADE20K val PSPNet (ResNet-152) mIoU 43.51% #90 of 95 Archive leaderboard report
Semantic Segmentation ADE20K val PSPNet (ResNet-101) mIoU 43.29% #91 of 95 Archive leaderboard report
Semantic Segmentation BDD100K val PSPNet mIoU 62.3 #6 of 24 Archive leaderboard report
Semantic Segmentation Cityscapes test PSPNet++ Mean IoU (class) 80.2% #51 of 105 Archive leaderboard report
Semantic Segmentation Cityscapes test PSPNet Mean IoU (class) 78.4% #60 of 105 Archive leaderboard report
Semantic Segmentation Cityscapes val PSPNet (Dilated-ResNet-101) mIoU 79.7 #56 of 99 Archive leaderboard report
Semantic Segmentation DADA-seg PSPNet (ResNet-101) mIoU 20.1 #20 of 28 Archive leaderboard report
Semantic Segmentation DensePASS PSPNet (ResNet-50) mIoU 29.5% #28 of 36 Archive leaderboard report
Semantic Segmentation Fine-Grained Grass Segmentation Dataset PSPNet mIoU 47.95 #6 of 10 Archive leaderboard report
Semantic Segmentation PASCAL Context PSPNet (ResNet-101) mIoU 47.8 #53 of 66 Archive leaderboard report
Semantic Segmentation PASCAL VOC 2012 test PSPNet Mean IoU 85.4% #10 of 51 Archive leaderboard report
Semantic Segmentation PASCAL VOC 2012 test PSPNet (ResNet-101) Mean IoU 82.6% #26 of 51 Archive leaderboard report
Semantic Segmentation Potsdam PSPNet mIoU 82.98 #11 of 11 Archive leaderboard report
Semantic Segmentation SELMA PSPNet mIoU 68.4 #5 of 7 Archive leaderboard report
Semantic Segmentation ScanNetV2 PSPNet Mean IoU 47.5% #9 of 12 Archive leaderboard report
Semantic Segmentation Trans10K PSPNet GFLOPs 187.03 #8 of 15 Archive leaderboard report
Semantic Segmentation Trans10K PSPNet mIoU 68.23% #8 of 15 Archive leaderboard report
Semantic Segmentation US3D PSNet mIoU 73.12 #9 of 11 Archive leaderboard report
Semantic Segmentation UrbanLF PSPNet mIoU (Real) 76.34 #11 of 14 Archive leaderboard report
Semantic Segmentation UrbanLF PSPNet mIoU (Syn) 75.78 #11 of 14 Archive leaderboard report
Semantic Segmentation Vaihingen PSPNet mIoU 76.79 #7 of 13 Archive leaderboard report
Thermal Image Segmentation MFN Dataset PSPNet mIOU 46.1 #47 of 55 Archive leaderboard report
Video Semantic Segmentation CamVid PSPNet-50 Mean IoU 76 #4 of 6 Archive leaderboard report
Video Semantic Segmentation Cityscapes val PSPNet-101 [20] mIoU 79.7 #4 of 9 Archive leaderboard report
Video Semantic Segmentation Cityscapes val PSPNet-50 [20] mIoU 78.1 #5 of 9 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

Introduced by this paper: PSPNet, Pyramid Pooling Module

1x1 ConvolutionAuxiliary ClassifierAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionDilated ConvolutionFCNGlobal Average PoolingKaiming InitializationMax PoolingPSPNetPolynomial Rate DecayPyramid Pooling ModuleRandom Gaussian BlurRandom Horizontal FlipRandomRotateReLUResidual BlockResidual ConnectionSGD with MomentumWeight Decay

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