Papers › SelfReformer: Self-Refined Network with Transformer for Salient Object Detection

SelfReformer: Self-Refined Network with Transformer for Salient Object Detection

23 May 2022arXiv:2205.11283archive 2025-07-28

Yi Ke Yun, Weisi Lin

The global and local contexts significantly contribute to the integrity of predictions in Salient Object Detection (SOD). Unfortunately, existing methods still struggle to generate complete predictions with fine details. There are two major problems in conventional approaches: first, for global context, high-level CNN-based encoder features cannot effectively catch long-range dependencies, resulting in incomplete predictions. Second, downsampling the ground truth to fit the size of predictions will introduce inaccuracy as the ground truth details are lost during interpolation or pooling. Thus, in this work, we developed a Transformer-based network and framed a supervised task for a branch to learn the global context information explicitly. Besides, we adopt Pixel Shuffle from Super-Resolution (SR) to reshape the predictions back to the size of ground truth instead of the reverse. Thus details in the ground truth are untouched. In addition, we developed a two-stage Context Refinement Module (CRM) to fuse global context and automatically locate and refine the local details in the predictions. The proposed network can guide and correct itself based on the global and local context generated, thus is named, Self-Refined Transformer (SelfReformer). Extensive experiments and evaluation results on five benchmark datasets demonstrate the outstanding performance of the network, and we achieved the state-of-the-art.

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 2 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) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

BarCodeReader/SelfReformer officialmentioned in papermentioned on GitHubpytorchBSD-3-ClauseSyntology: 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

2 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) · 0 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

Licence: 0 of the 2 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 BarCodeReader/SelfReformer. “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.

BarCodeReader/SelfReformer official repository 2 samples, 2 ran (0 instrument-failed) · 0 unverified
calculate_mae utils.py ran fingerprinted BSD-3-Clause (permissive) · 8a3ba66f381601bc · report fixture: signature img1:ndarray/3/int, img2:ndarray/3/int · returned float64 · level recorded 2026-09-24
get_sinusoid_encoding in 24 papers model/Transformer.py ran · honoured contract fingerprinted BSD-3-Clause (permissive) · ced6bc2bfdfe0059 · report fixture: signature n_position:int/0/int, d_hid:int/0/int · returned Tensor · level recorded 2026-09-22

Tasks

Object DetectionSalient Object DetectionSuper-Resolutionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Salient Object Detection DUT-OMRON SelfReformer-Swin E-measure 0.884 #4 of 8 Archive leaderboard report
Salient Object Detection DUT-OMRON SelfReformer-Swin MAE 0.043 #4 of 8 Archive leaderboard report
Salient Object Detection DUT-OMRON SelfReformer-Swin S-measure 0.859 #4 of 8 Archive leaderboard report
Salient Object Detection DUT-OMRON SelfReformer-Swin max_F1 0.838 #4 of 8 Archive leaderboard report
Salient Object Detection DUT-OMRON SelfReformer E-measure 0.886 #5 of 8 Archive leaderboard report
Salient Object Detection DUT-OMRON SelfReformer MAE 0.041 #5 of 8 Archive leaderboard report
Salient Object Detection DUT-OMRON SelfReformer S-measure 0.856 #5 of 8 Archive leaderboard report
Salient Object Detection DUT-OMRON SelfReformer max_F1 0.836 #5 of 8 Archive leaderboard report
Salient Object Detection DUTS-TE SelfReformer-Swin E-measure 0.924 #3 of 8 Archive leaderboard report
Salient Object Detection DUTS-TE SelfReformer-Swin MAE 0.024 #3 of 8 Archive leaderboard report
Salient Object Detection DUTS-TE SelfReformer-Swin Smeasure 0.921 #3 of 8 Archive leaderboard report
Salient Object Detection DUTS-TE SelfReformer-Swin max_F1 0.925 #3 of 8 Archive leaderboard report
Salient Object Detection DUTS-TE SelfReformer E-measure 0.920 #5 of 8 Archive leaderboard report
Salient Object Detection DUTS-TE SelfReformer MAE 0.026 #5 of 8 Archive leaderboard report
Salient Object Detection DUTS-TE SelfReformer Smeasure 0.911 #5 of 8 Archive leaderboard report
Salient Object Detection DUTS-TE SelfReformer max_F1 0.916 #5 of 8 Archive leaderboard report
Salient Object Detection ECSSD SelfReformer-Swin E-measure 0.935 #3 of 10 Archive leaderboard report
Salient Object Detection ECSSD SelfReformer-Swin MAE 0.025 #3 of 10 Archive leaderboard report
Salient Object Detection ECSSD SelfReformer-Swin S-measure 0.941 #3 of 10 Archive leaderboard report
Salient Object Detection ECSSD SelfReformer-Swin max_F1 0.963 #3 of 10 Archive leaderboard report
Salient Object Detection ECSSD SelfReformer E-measure 0.928 #6 of 10 Archive leaderboard report
Salient Object Detection ECSSD SelfReformer MAE 0.027 #6 of 10 Archive leaderboard report
Salient Object Detection ECSSD SelfReformer S-measure 0.935 #6 of 10 Archive leaderboard report
Salient Object Detection ECSSD SelfReformer max_F1 0.957 #6 of 10 Archive leaderboard report
Salient Object Detection HKU-IS SelfReformer-Swin E-measure 0.961 #3 of 9 Archive leaderboard report
Salient Object Detection HKU-IS SelfReformer-Swin MAE 0.023 #3 of 9 Archive leaderboard report
Salient Object Detection HKU-IS SelfReformer-Swin S-measure 0.934 #3 of 9 Archive leaderboard report
Salient Object Detection HKU-IS SelfReformer-Swin max_F1 0.952 #3 of 9 Archive leaderboard report
Salient Object Detection HKU-IS SelfReformer E-measure 0.959 #5 of 9 Archive leaderboard report
Salient Object Detection HKU-IS SelfReformer MAE 0.024 #5 of 9 Archive leaderboard report
Salient Object Detection HKU-IS SelfReformer S-measure 0.930 #5 of 9 Archive leaderboard report
Salient Object Detection HKU-IS SelfReformer max_F1 0.947 #5 of 9 Archive leaderboard report
Salient Object Detection PASCAL-S SelfReformer-Swin E-measure 0.874 #5 of 10 Archive leaderboard report
Salient Object Detection PASCAL-S SelfReformer-Swin MAE 0.049 #5 of 10 Archive leaderboard report
Salient Object Detection PASCAL-S SelfReformer-Swin S-measure 0.877 #5 of 10 Archive leaderboard report
Salient Object Detection PASCAL-S SelfReformer-Swin max_F1 0.896 #5 of 10 Archive leaderboard report
Salient Object Detection PASCAL-S SelfReformer E-measure 0.872 #6 of 10 Archive leaderboard report
Salient Object Detection PASCAL-S SelfReformer MAE 0.050 #6 of 10 Archive leaderboard report
Salient Object Detection PASCAL-S SelfReformer S-measure 0.874 #6 of 10 Archive leaderboard report
Salient Object Detection PASCAL-S SelfReformer max_F1 0.894 #6 of 10 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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