Papers › Semantic Flow for Fast and Accurate Scene Parsing

Semantic Flow for Fast and Accurate Scene Parsing

24 Feb 2020ECCV 2020 8arXiv:2002.10120archive 2025-07-28

Xiangtai Li, Ansheng You, Zhen Zhu, Houlong Zhao, Maoke Yang, Kuiyuan Yang, Yunhai Tong

In this paper, we focus on designing effective method for fast and accurate scene parsing. A common practice to improve the performance is to attain high resolution feature maps with strong semantic representation. Two strategies are widely used -- atrous convolutions and feature pyramid fusion, are either computation intensive or ineffective. Inspired by the Optical Flow for motion alignment between adjacent video frames, we propose a Flow Alignment Module (FAM) to learn Semantic Flow between feature maps of adjacent levels, and broadcast high-level features to high resolution features effectively and efficiently. Furthermore, integrating our module to a common feature pyramid structure exhibits superior performance over other real-time methods even on light-weight backbone networks, such as ResNet-18. Extensive experiments are conducted on several challenging datasets, including Cityscapes, PASCAL Context, ADE20K and CamVid. Especially, our network is the first to achieve 80.4\% mIoU on Cityscapes with a frame rate of 26 FPS. The code is available at \url{https://github.com/lxtGH/SFSegNets}.

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="2002.10120")

Code

Syntology Ran 1 of 8 code samples harvested from 2 repositories linked to this paper; 7 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: official repository: 5 samples from 1 repository, 0 ran; community (archive-listed): 2 samples from 1 repository, 0 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

donnyyou/torchcv officialmentioned in paperpytorchApache-2.0 report
lxtGH/SFSegNets officialmentioned in paperpytorch report
MaybeShewill-CV/sfnet-tensorflow mentioned on GitHubtfnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-ready report
Shualite/SFNet.pytorch mentioned on GitHubpytorch report
sithu31296/semantic-segmentation mentioned on GitHubpytorch 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

8 samples harvested; 1 ran; 0 honoured the contract we drafted; 7 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 · our draft was wrong
7unverified

Licence: 1 of the 8 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 2 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.

assert_tensor_type donnyyou/torchcv/lib/parallel/data_container.py official repository unverified Apache-2.0 (permissive) · 4a6bd97bd6bba0ad · report
get_input_device donnyyou/torchcv/lib/parallel/_functions.py official repository unverified Apache-2.0 (permissive) · 72b89f53f5854825 · report
scatter donnyyou/torchcv/lib/parallel/_functions.py official repository unverified Apache-2.0 (permissive) · aa73f0787179b863 · report
scatter donnyyou/torchcv/lib/parallel/scatter_gather.py official repository unverified Apache-2.0 (permissive) · 12610892f9cebded · report
scatter_kwargs donnyyou/torchcv/lib/parallel/scatter_gather.py official repository unverified Apache-2.0 (permissive) · ea53ec023a304e67 · report
sf_resnet18 Shualite/SFNet.pytorch/sfnet/sfnet.py community (archive-listed) unverified MIT (permissive) · 1b772e24adfd25a7 · report
sf_resnet34 Shualite/SFNet.pytorch/sfnet/sfnet.py community (archive-listed) unverified MIT (permissive) · b749652595868268 · report
conv3x3 identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · fac5364e2f53c6db · report

Tasks

Optical Flow EstimationReal-Time Semantic SegmentationScene ParsingSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Real-Time Semantic Segmentation Cityscapes test SFNet-R18 Frame (fps) 25.7(1080Ti) #2 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test SFNet-R18 Time (ms) 39.2 #2 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test SFNet-R18 mIoU 80.4% #2 of 39 Archive leaderboard report
Semantic Segmentation BDD100K val SFNet(DF2) mIoU 60.2(208FPS 4090) #19 of 24 Archive leaderboard report
Semantic Segmentation BDD100K val SFNet(DF1) mIoU 55.4(70.3fps) #20 of 24 Archive leaderboard report
Semantic Segmentation BDD100K val SFNet(ResNet-18) mIoU 60.6(132.5FPS 4090) #21 of 24 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: Flow Alignment Module

ConvolutionFlow Alignment Module

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