Papers › CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and...

CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement

6 May 2020CVPR 2020 6arXiv:2005.02551archive 2025-07-28

Ho Kei Cheng, Jihoon Chung, Yu-Wing Tai, Chi-Keung Tang

State-of-the-art semantic segmentation methods were almost exclusively trained on images within a fixed resolution range. These segmentations are inaccurate for very high-resolution images since using bicubic upsampling of low-resolution segmentation does not adequately capture high-resolution details along object boundaries. In this paper, we propose a novel approach to address the high-resolution segmentation problem without using any high-resolution training data. The key insight is our CascadePSP network which refines and corrects local boundaries whenever possible. Although our network is trained with low-resolution segmentation data, our method is applicable to any resolution even for very high-resolution images larger than 4K. We present quantitative and qualitative studies on different datasets to show that CascadePSP can reveal pixel-accurate segmentation boundaries using our novel refinement module without any finetuning. Thus, our method can be regarded as class-agnostic. Finally, we demonstrate the application of our model to scene parsing in multi-class segmentation.

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 7 code samples harvested from 1 repository linked to this paper: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 7 samples from 1 repository, 2 ran (2 with no instrument failure; 0 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 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

hkchengrex/CascadePSP officialmentioned in papermentioned on GitHubpytorchMITSyntology: 7 samples, 2 ran (0 instrument-failed) · 5 unverified report
earth-insights/ClassTrans mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Aligning and Prompting Everything All at Once for Universal Visual Perception (arXiv:2312.02153; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. 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

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

1ran · honoured contract
1ran
5unverified

Licence: 2 of the 7 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from hkchengrex/CascadePSP. “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.

hkchengrex/CascadePSP official repository 7 samples, 2 ran (0 instrument-failed) · 5 unverified
color_map in 15 papers eval_post_ade.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · fcbd501f30a007d4 · report fixture: signature N:int/0/int, normalized:bool/0/bool · returned ndarray · level recorded 2026-09-22
conv3x3 in 1,376 papers models/psp/extractors.py ran MIT (permissive) here; the stored copy is pointer only · 48f5a5ec1d5dd2ef · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, dilation:int/0/int · returned Conv2d · level recorded 2026-09-24
get_bb_position dataset/make_bb_trans.py unverified MIT (permissive) · 58be3f0953cafaef · report
get_iu eval_post.py unverified MIT (permissive) · f5f76587ff3a7654 · report
is_bb_overlap dataset/make_bb_trans.py unverified MIT (permissive) · 5894805c2d7c5b80 · report
safe_forward eval_helper.py unverified MIT (permissive) · 9233f30dee14c56f · report
scale_bb_by dataset/make_bb_trans.py unverified MIT (permissive) · a190282758f268f5 · report

Tasks

4kLand Cover ClassificationScene ParsingSegmentationSemantic Segmentation

Datasets

Introduced by this paper, per the archive.

BIG

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation BIG PSPNet + CascadePSP IoU 93.93 #1 of 4 Archive leaderboard report
Semantic Segmentation BIG PSPNet + CascadePSP mBA 75.32 #1 of 4 Archive leaderboard report
Semantic Segmentation BIG RefineNet + CascadePSP IoU 92.79 #2 of 4 Archive leaderboard report
Semantic Segmentation BIG RefineNet + CascadePSP mBA 74.77 #2 of 4 Archive leaderboard report
Semantic Segmentation BIG DeepLabV3+ + CascadePSP IoU 92.23 #3 of 4 Archive leaderboard report
Semantic Segmentation BIG DeepLabV3+ + CascadePSP mBA 74.59 #3 of 4 Archive leaderboard report
Semantic Segmentation BIG FCN + CascadePSP IoU 77.87 #4 of 4 Archive leaderboard report
Semantic Segmentation BIG FCN + CascadePSP mBA 67.04 #4 of 4 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: CascadePSP

CascadePSP

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