Papers › ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation

ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation

19 Mar 2018ECCV 2018 9arXiv:1803.06815archive 2025-07-28

Sachin Mehta, Mohammad Rastegari, Anat Caspi, Linda Shapiro, Hannaneh Hajishirzi

We introduce a fast and efficient convolutional neural network, ESPNet, for semantic segmentation of high resolution images under resource constraints. ESPNet is based on a new convolutional module, efficient spatial pyramid (ESP), which is efficient in terms of computation, memory, and power. ESPNet is 22 times faster (on a standard GPU) and 180 times smaller than the state-of-the-art semantic segmentation network PSPNet, while its category-wise accuracy is only 8% less. We evaluated ESPNet on a variety of semantic segmentation datasets including Cityscapes, PASCAL VOC, and a breast biopsy whole slide image dataset. Under the same constraints on memory and computation, ESPNet outperforms all the current efficient CNN networks such as MobileNet, ShuffleNet, and ENet on both standard metrics and our newly introduced performance metrics that measure efficiency on edge devices. Our network can process high resolution images at a rate of 112 and 9 frames per second on a standard GPU and edge device, respectively.

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 10 code samples harvested from 3 repositories linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 9 samples from 2 repositories, 9 ran (7 with no instrument failure; 2 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 3 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.

sacmehta/ESPNet officialmentioned in papermentioned on GitHubpytorchMITSyntology: 1 sample, 0 ran · 1 unverified report
klintan/lanenet-pytorch mentioned on GitHubpytorchMITSyntology: not harvested report
klintan/pytorch-lanenet mentioned on GitHubpytorchMITSyntology: not harvested report
sacmehta/3d-espnet mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
sacmehta/EdgeNets mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DiCENet: Dimension-wise Convolutions for Efficient Networks (arXiv:1906.03516; 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
zh320/realtime-semantic-segmentation-pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to CGNet: A Light-weight Context Guided Network for Semantic Segmentation (arXiv:1811.08201; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified), ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network (arXiv:1811.11431; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified), Lite-HRNet: A Lightweight High-Resolution Network (arXiv:2104.06403; that paper's own run record: 13 ran (of which 2 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 16 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. 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
simuler/ESPNet paddleApache-2.0Syntology: 7 samples, 7 ran (2 instrument-failed) · 0 unverified 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

10 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 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.

2ran · honoured contract
2ran · our draft was wrong
5ran
1unverified

Licence: 0 of the 10 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 3 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.

sacmehta/ESPNet official repository 1 sample, 0 ran · 1 unverified
make_dot in 11 papers train/VisualizeGraph.py unverified MIT (permissive) · 8456f0fd622b9df9 · report
sacmehta/3d-espnet community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
diceFunction ComputeDice.py ran · honoured contract fingerprinted MIT (permissive) · 7b21a1e5f7422c2f · report fixture: signature im1:ndarray/3/int, im2:ndarray/3/int · returned float64 · level recorded 2026-09-22
norm in 120 papers
census: 23 implementations from 26 papers, 15 distinct outputs across 6 buckets, one shared input per bucket this sample: bucket 6 of 6, arg 1: rank 2, kind int, dtype uint8
ComputeDice.py ran · honoured contract fingerprinted MIT (permissive) · 8cedd657c11f6f8c · report fixture: signature im:ndarray/2/int · returned ndarray · level recorded 2026-09-22
simuler/ESPNet community (archive-listed) 7 samples, 7 ran (2 instrument-failed) · 0 unverified
compute_class_weights in 6 papers compute_classweight.py ran Apache-2.0 (permissive) · e4705748c848babe · report fixture: signature histogram:ndarray/1/float · returned ndarray · level recorded 2026-09-26
flip_combination in 8 papers paddleseg/core/infer.py ran Apache-2.0 (permissive) · 95bccf5957a196e4 · report fixture: signature flip_horizontal:bool/0/bool, flip_vertical:bool/0/bool · returned list · level recorded 2026-09-24
get_reverse_list in 8 papers paddleseg/core/infer.py ran Apache-2.0 (permissive) · a5dbdd4f2d59692e · report fixture: signature ori_shape:list/1/int, transforms:list/1/Resize · returned list · level recorded 2026-09-26
get_test_config in 9 papers val.py ran · our draft was wrong Apache-2.0 (permissive) · 20eb3e6b0aba73e4 · report fixture: signature cfg:SimpleConfig/0/?, args:SimpleArgs/0/? · returned dict · level recorded 2026-09-22
get_test_config in 9 papers predict.py ran Apache-2.0 (permissive) · 0b3ec74bd2e5ed5d · report fixture: signature cfg:MockConfig/0/?, args:MockArgs/0/? · returned dict · level recorded 2026-09-26
partition_list in 10 papers paddleseg/core/predict.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 2f75a098ce9f7b0e · report fixture: signature arr:list/1/int, m:int/0/int · returned list · level recorded 2026-09-22
readFile in 6 papers compute_classweight.py ran Apache-2.0 (permissive) · 9c1bd7a7658cc12c · report fixture: signature data_dir:str/0/str, fileName:str/0/str · returned ndarray · level recorded 2026-09-26

Tasks

Panoptic SegmentationReal-Time Semantic SegmentationSegmentationSemantic Segmentation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation Cityscapes test ESPNet Mean IoU (class) 60.3% #100 of 105 Archive leaderboard report
Semantic Segmentation PASCAL VOC 2012 test ESPNet Mean IoU 63.01% #48 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

Introduced by this paper: ESPNet, Hierarchical Feature Fusion

1x1 ConvolutionAdamConvolutionDilated ConvolutionESPESPNetHierarchical Feature FusionKaiming InitializationPReLUPointwise ConvolutionRandom Horizontal FlipRandom Resized CropRandom ScalingStep DecayWeight 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