Papers › Revisiting Image Pyramid Structure for High Resolution Salient Object Detection

Revisiting Image Pyramid Structure for High Resolution Salient Object Detection

20 Sep 2022arXiv:2209.09475archive 2025-07-28

Taehun Kim, Kunhee Kim, Joonyeong Lee, Dongmin Cha, Jiho Lee, Daijin Kim

Salient object detection (SOD) has been in the spotlight recently, yet has been studied less for high-resolution (HR) images. Unfortunately, HR images and their pixel-level annotations are certainly more labor-intensive and time-consuming compared to low-resolution (LR) images and annotations. Therefore, we propose an image pyramid-based SOD framework, Inverse Saliency Pyramid Reconstruction Network (InSPyReNet), for HR prediction without any of HR datasets. We design InSPyReNet to produce a strict image pyramid structure of saliency map, which enables to ensemble multiple results with pyramid-based image blending. For HR prediction, we design a pyramid blending method which synthesizes two different image pyramids from a pair of LR and HR scale from the same image to overcome effective receptive field (ERF) discrepancy. Our extensive evaluations on public LR and HR SOD benchmarks demonstrate that InSPyReNet surpasses the State-of-the-Art (SotA) methods on various SOD metrics and boundary accuracy.

PaperPDFCodeCode 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 11 code samples harvested from 3 repositories linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 2 repositories, 8 ran (5 with no instrument failure; 3 where Syntology's instrument failed); community (archive-listed): 2 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.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 10 samples that ran have no recorded date.

plemeri/inspyrenet officialmentioned in papermentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
plemeri/transparent-background officialpytorchMITSyntology: 8 samples, 7 ran (2 instrument-failed) · 1 unverified report
john-mnz/ComfyUI-Inspyrenet-Rembg pytorchMITSyntology: 2 samples, 2 ran (0 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.

Code Syntology ran Syntology

11 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 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 · our draft was wrong
1ran; the contract check could not run
7ran
1unverified

Licence: 0 of the 11 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.

plemeri/inspyrenet official repository 1 sample, 1 ran (1 instrument-failed) · 0 unverified
get_format run/Inference.py ran · our draft was wrong MIT (permissive) · 1eadaf408af1168c · report fixture: signature source:list/1/str · returned str · level recorded 2026-09-22
plemeri/transparent-background official repository 8 samples, 7 ran (2 instrument-failed) · 1 unverified
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
transparent_background/backbones/SwinTransformer.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 144d10b49baeb8a6 · report fixture: signature x:Tensor/4/float, window_size:int/0/int · returned Tensor · level recorded, date not recorded
get_format transparent_background/utils.py ran MIT (permissive) · ad87b881b49f3704 · report fixture: signature source:list/1/str · returned str · level recorded 2026-09-25
is_float in 14 papers transparent_background/gui.py ran MIT (permissive) · 614f3ec915d613e1 · report fixture: signature str:str/0/str · returned bool · level recorded 2026-09-25
load_config in 389 papers transparent_background/utils.py ran MIT (permissive) · e8b1d6c6640e3379 · report fixture: signature config_dir:str/0/str, easy:bool/0/bool · returned EasyDict · level recorded 2026-09-25
sort in 12 papers transparent_background/utils.py ran MIT (permissive) · b0d5bca317b4e704 · report fixture: signature x:list/1/str · returned list · level recorded 2026-09-25
to_base64 transparent_background/Remover.py ran MIT (permissive) · 32148520ac8a75d3 · report fixture: signature image:Image/0/? · returned str · level recorded 2026-09-25
window_reverse in 296 papers transparent_background/backbones/SwinTransformer.py ran · our draft was wrong MIT (permissive) · 61bf152e6a42a184 · report fixture: signature windows:Tensor/4/float, window_size:int/0/int, H:int/0/int, W:int/0/int · returned Tensor · level recorded, date not recorded
SwinT transparent_background/backbones/SwinTransformer.py unverified MIT (permissive) · 514e23fec6c636e1 · report
john-mnz/ComfyUI-Inspyrenet-Rembg community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
pil2tensor in 5 papers Inspyrenet_Rembg.py ran MIT (permissive) · ddd740751dbbd55b · report fixture: signature image:Image/0/? · returned Tensor · level recorded 2026-09-25
tensor2pil in 5 papers Inspyrenet_Rembg.py ran MIT (permissive) · ee8ddf2c7607bd81 · report fixture: signature image:Tensor/3/float · returned Image · level recorded 2026-09-25

Tasks

Dichotomous Image SegmentationObject DetectionRGB Salient Object DetectionSalient Object DetectionVocal Bursts Intensity Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Dichotomous Image Segmentation DIS-TE1 InSPyReNet (HR scale) E-measure 0.894 #4 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 InSPyReNet (HR scale) HCE 110 #4 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 InSPyReNet (HR scale) MAE 0.045 #4 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 InSPyReNet (HR scale) S-Measure 0.873 #4 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 InSPyReNet (HR scale) max F-Measure 0.845 #4 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 InSPyReNet (HR scale) weighted F-measure 0.788 #4 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 InSPyReNet HCE 148 #5 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 InSPyReNet S-Measure 0.862 #5 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 InSPyReNet max F-Measure 0.834 #5 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 InSPyReNet (HR scale) HCE 255 #4 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 InSPyReNet (HR scale) S-Measure 0.905 #4 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 InSPyReNet (HR scale) max F-Measure 0.894 #4 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 InSPyReNet E-measure 0.925 #5 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 InSPyReNet HCE 316 #5 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 InSPyReNet MAE 0.038 #5 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 InSPyReNet S-Measure 0.893 #5 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 InSPyReNet max F-Measure 0.881 #5 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 InSPyReNet weighted F-measure 0.834 #5 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 InSPyReNet (HR scale) E-measure 0.938 #4 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 InSPyReNet (HR scale) HCE 522 #4 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 InSPyReNet (HR scale) MAE 0.034 #4 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 InSPyReNet (HR scale) S-Measure 0.918 #4 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 InSPyReNet (HR scale) max F-Measure 0.919 #4 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 InSPyReNet (HR scale) weighted F-measure 0.871 #4 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 InSPyReNet E-measure 0.938 #5 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 InSPyReNet HCE 582 #5 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 InSPyReNet MAE 0.038 #5 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 InSPyReNet S-Measure 0.902 #5 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 InSPyReNet max F-Measure 0.904 #5 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 InSPyReNet weighted F-measure 0.856 #5 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 InSPyReNet (HR scale) E-measure 0.926 #3 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 InSPyReNet (HR scale) HCE 2336 #3 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 InSPyReNet (HR scale) MAE 0.042 #3 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 InSPyReNet (HR scale) S-Measure 0.905 #3 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 InSPyReNet (HR scale) max F-Measure 0.905 #3 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 InSPyReNet (HR scale) weighted F-measure 0.848 #3 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 InSPyReNet E-measure 0.926 #5 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 InSPyReNet HCE 2243 #5 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 InSPyReNet MAE 0.046 #5 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 InSPyReNet S-Measure 0.891 #5 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 InSPyReNet max F-Measure 0.892 #5 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 InSPyReNet weighted F-measure 0.840 #5 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD InSPyReNet (HR scale) HCE 904 #6 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD InSPyReNet (HR scale) S-Measure 0.900 #6 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD InSPyReNet (HR scale) max F-Measure 0.889 #6 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD InSPyReNet E-measure 0.921 #7 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD InSPyReNet HCE 905 #7 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD InSPyReNet MAE 0.043 #7 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD InSPyReNet S-Measure 0.887 #7 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD InSPyReNet max F-Measure 0.876 #7 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD InSPyReNet weighted F-measure 0.826 #7 of 24 Archive leaderboard report
RGB Salient Object Detection DAVIS-S InSPyReNet (DUTS, HRSOD) F-measure 0.976 #5 of 12 Archive leaderboard report
RGB Salient Object Detection DAVIS-S InSPyReNet (DUTS, HRSOD) S-measure 0.972 #5 of 12 Archive leaderboard report
RGB Salient Object Detection DAVIS-S InSPyReNet (DUTS, HRSOD) mBA 0.770 #5 of 12 Archive leaderboard report
RGB Salient Object Detection DAVIS-S InSPyReNet F-measure 0.959 #7 of 12 Archive leaderboard report
RGB Salient Object Detection DAVIS-S InSPyReNet MAE 0.009 #7 of 12 Archive leaderboard report
RGB Salient Object Detection DAVIS-S InSPyReNet S-measure 0.962 #7 of 12 Archive leaderboard report
RGB Salient Object Detection DAVIS-S InSPyReNet mBA 0.743 #7 of 12 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON InSPyReNet F-measure 0.832 #3 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON InSPyReNet MAE 0.045 #3 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON InSPyReNet S-Measure 0.875 #3 of 18 Archive leaderboard report
RGB Salient Object Detection DUTS-TE InSPyReNet MAE 0.024 #6 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE InSPyReNet S-Measure 0.931 #6 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE InSPyReNet max F-measure 0.892 #6 of 31 Archive leaderboard report
RGB Salient Object Detection ECSSD InSPyReNet F-measure 0.96 #2 of 14 Archive leaderboard report
RGB Salient Object Detection ECSSD InSPyReNet MAE 0.031 #2 of 14 Archive leaderboard report
RGB Salient Object Detection ECSSD InSPyReNet S-Measure 0.936 #2 of 14 Archive leaderboard report
RGB Salient Object Detection HKU-IS InSPyReNet F-measure 0.955 #1 of 14 Archive leaderboard report
RGB Salient Object Detection HKU-IS InSPyReNet MAE 0.028 #1 of 14 Archive leaderboard report
RGB Salient Object Detection HKU-IS InSPyReNet S-Measure 0.944 #1 of 14 Archive leaderboard report
RGB Salient Object Detection HRSOD InSPyReNet (DUTS, HRSOD) MAE 0.014 #4 of 14 Archive leaderboard report
RGB Salient Object Detection HRSOD InSPyReNet (DUTS, HRSOD) S-Measure 0.960 #4 of 14 Archive leaderboard report
RGB Salient Object Detection HRSOD InSPyReNet (DUTS, HRSOD) mBA 0.766 #4 of 14 Archive leaderboard report
RGB Salient Object Detection HRSOD InSPyReNet (DUTS, HRSOD) max F-Measure 0.957 #4 of 14 Archive leaderboard report
RGB Salient Object Detection HRSOD InSPyReNet (HRSOD, UHRSD) MAE 0.018 #7 of 14 Archive leaderboard report
RGB Salient Object Detection HRSOD InSPyReNet (HRSOD, UHRSD) S-Measure 0.956 #7 of 14 Archive leaderboard report
RGB Salient Object Detection HRSOD InSPyReNet (HRSOD, UHRSD) mBA 0.771 #7 of 14 Archive leaderboard report
RGB Salient Object Detection HRSOD InSPyReNet (HRSOD, UHRSD) max F-Measure 0.956 #7 of 14 Archive leaderboard report
RGB Salient Object Detection HRSOD InSPyReNet MAE 0.016 #9 of 14 Archive leaderboard report
RGB Salient Object Detection HRSOD InSPyReNet S-Measure 0.952 #9 of 14 Archive leaderboard report
RGB Salient Object Detection HRSOD InSPyReNet mBA 0.738 #9 of 14 Archive leaderboard report
RGB Salient Object Detection HRSOD InSPyReNet max F-Measure 0.949 #9 of 14 Archive leaderboard report
RGB Salient Object Detection PASCAL-S InSPyReNet F-measure 0.893 #2 of 13 Archive leaderboard report
RGB Salient Object Detection PASCAL-S InSPyReNet MAE 0.048 #2 of 13 Archive leaderboard report
RGB Salient Object Detection PASCAL-S InSPyReNet S-Measure 0.893 #2 of 13 Archive leaderboard report
RGB Salient Object Detection UHRSD InSPyReNet (HRSOD, UHRSD) MAE 0.020 #3 of 12 Archive leaderboard report
RGB Salient Object Detection UHRSD InSPyReNet (HRSOD, UHRSD) S-Measure 0.953 #3 of 12 Archive leaderboard report
RGB Salient Object Detection UHRSD InSPyReNet (HRSOD, UHRSD) mBA 0.812 #3 of 12 Archive leaderboard report
RGB Salient Object Detection UHRSD InSPyReNet (HRSOD, UHRSD) max F-Measure 0.957 #3 of 12 Archive leaderboard report
RGB Salient Object Detection UHRSD InSPyReNet (DUTS, HRSOD) S-Measure 0.936 #7 of 12 Archive leaderboard report
RGB Salient Object Detection UHRSD InSPyReNet (DUTS, HRSOD) mBA 0.785 #7 of 12 Archive leaderboard report
RGB Salient Object Detection UHRSD InSPyReNet MAE 0.029 #9 of 12 Archive leaderboard report
RGB Salient Object Detection UHRSD InSPyReNet S-Measure 0.932 #9 of 12 Archive leaderboard report
RGB Salient Object Detection UHRSD InSPyReNet mBA 0.741 #9 of 12 Archive leaderboard report
RGB Salient Object Detection UHRSD InSPyReNet max F-Measure 0.938 #9 of 12 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

AttentionAxial AttentionDense ConnectionsLaplacian PyramidLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSoftmaxVision Transformer

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