Papers › ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network

ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network

28 Nov 2018CVPR 2019 6arXiv:1811.11431archive 2025-07-28

Sachin Mehta, Mohammad Rastegari, Linda Shapiro, Hannaneh Hajishirzi

We introduce a light-weight, power efficient, and general purpose convolutional neural network, ESPNetv2, for modeling visual and sequential data. Our network uses group point-wise and depth-wise dilated separable convolutions to learn representations from a large effective receptive field with fewer FLOPs and parameters. The performance of our network is evaluated on four different tasks: (1) object classification, (2) semantic segmentation, (3) object detection, and (4) language modeling. Experiments on these tasks, including image classification on the ImageNet and language modeling on the PenTree bank dataset, demonstrate the superior performance of our method over the state-of-the-art methods. Our network outperforms ESPNet by 4-5% and has 2-4x fewer FLOPs on the PASCAL VOC and the Cityscapes dataset. Compared to YOLOv2 on the MS-COCO object detection, ESPNetv2 delivers 4.4% higher accuracy with 6x fewer FLOPs. Our experiments show that ESPNetv2 is much more power efficient than existing state-of-the-art efficient methods including ShuffleNets and MobileNets. Our code is open-source and available at https://github.com/sacmehta/ESPNetv2

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="1811.11431")

Code

Syntology Ran 2 of 4 code samples harvested from 2 repositories linked to this paper; 2 have no recorded run. Of those that ran: 2 ran · our draft was wrong.

By repository: community (archive-listed): 4 samples from 2 repositories, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

sacmehta/EdgeNets officialmentioned on GitHubpytorchMIT report
ShigemichiMatsuzaki/MSPL mentioned on GitHubpytorchNOASSERTION report
ikuto056/Estimating_Distance mentioned on GitHubpytorch report
justld/EspnetV2_paddle mentioned on GitHubpaddle report
oki5656/Estimating_Distance mentioned on GitHubpytorch report
osmr/imgclsmob mentioned on GitHubmxnetMIT report
sacmehta/espnetv2-coreml mentioned on GitHubpytorchNOASSERTION 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

4 samples harvested; 2 ran; 0 honoured the contract we drafted; 2 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.

2ran · our draft was wrong
2unverified

Licence: 0 of the 4 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 2 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.

build_blocks zh320/realtime-semantic-segmentation-pytorch/models/espnetv2.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · 43f8cfd6793d23f0 · report
partition_list jonny4929/PaddleSeg_espnetv2/paddleseg/core/predict.py community (archive-listed) ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 2f75a098ce9f7b0e · report
flip_combination jonny4929/PaddleSeg_espnetv2/paddleseg/core/infer.py community (archive-listed) unverified Apache-2.0 (permissive) · 95bccf5957a196e4 · report
get_reverse_list jonny4929/PaddleSeg_espnetv2/paddleseg/core/infer.py community (archive-listed) unverified Apache-2.0 (permissive) · 026fee631ce4a66c · report

Tasks

General ClassificationImage ClassificationLanguage ModelingLanguage ModellingObjectObject DetectionReal-Time Object DetectionReal-Time Semantic SegmentationSemantic Segmentationimage-classificationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet ESPNetv2 GFLOPs 0.602 #967 of 1060 Archive leaderboard report
Image Classification ImageNet ESPNetv2 Number of params 5.9M #967 of 1060 Archive leaderboard report
Image Classification ImageNet ESPNetv2 Top 1 Accuracy 74.9% #967 of 1060 Archive leaderboard report
Semantic Segmentation Cityscapes test ESPNetv2 Mean IoU (class) 66.2% #94 of 105 Archive leaderboard report
Semantic Segmentation PASCAL VOC 2012 test ESPNetv2 Mean IoU 68.0% #41 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: EESP, ESPNetv2, Strided EESP

1x1 ConvolutionAverage PoolingBatch NormalizationConcatenated Skip ConnectionConvolutionCyclical Learning Rate PolicyDense ConnectionsDepthwise ConvolutionDepthwise Dilated Separable ConvolutionDepthwise Separable ConvolutionDilated ConvolutionDropoutEESPERUESPESPNetESPNetv2Global Average PoolingGrouped ConvolutionGroupwise Point ConvolutionHierarchical Feature FusionKaiming InitializationLSTMPReLUPointwise ConvolutionRandom Horizontal FlipRandom Resized CropResidual ConnectionSGDSigmoid ActivationSoftmaxStrided EESPTanh Activation

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