Papers › A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation,...

A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection

9 Mar 2022arXiv:2203.04708archive 2025-07-28

Yukun Su, Jingliang Deng, Ruizhou Sun, Guosheng Lin, Qingyao Wu

Humans tend to mine objects by learning from a group of images or several frames of video since we live in a dynamic world. In the computer vision area, many researches focus on co-segmentation (CoS), co-saliency detection (CoSD) and video salient object detection (VSOD) to discover the co-occurrent objects. However, previous approaches design different networks on these similar tasks separately, and they are difficult to apply to each other, which lowers the upper bound of the transferability of deep learning frameworks. Besides, they fail to take full advantage of the cues among inter- and intra-feature within a group of images. In this paper, we introduce a unified framework to tackle these issues, term as UFO (Unified Framework for Co-Object Segmentation). Specifically, we first introduce a transformer block, which views the image feature as a patch token and then captures their long-range dependencies through the self-attention mechanism. This can help the network to excavate the patch structured similarities among the relevant objects. Furthermore, we propose an intra-MLP learning module to produce self-mask to enhance the network to avoid partial activation. Extensive experiments on four CoS benchmarks (PASCAL, iCoseg, Internet and MSRC), three CoSD benchmarks (Cosal2015, CoSOD3k, and CocA) and four VSOD benchmarks (DAVIS16, FBMS, ViSal and SegV2) show that our method outperforms other state-of-the-arts on three different tasks in both accuracy and speed by using the same network architecture , which can reach 140 FPS in real-time.

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 13 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 13 samples from 1 repository, 12 ran (12 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

suyukun666/UFO officialmentioned in papermentioned on GitHubpytorchMITSyntology: 13 samples, 12 ran (0 instrument-failed) · 1 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

13 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 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.

12ran
1unverified

Licence: 0 of the 13 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 suyukun666/UFO. “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.

suyukun666/UFO official repository 13 samples, 12 ran (0 instrument-failed) · 1 unverified
Idx demo_matching.py ran fingerprinted MIT (permissive) · b17f0cf589616633 · report fixture: signature cur:int/0/int, ii:int/0/int, jj:int/0/int · returned int · level recorded 2026-09-24
cal_fmeasure misc.py ran MIT (permissive) · dbdcf302f4b3a47c · report fixture: signature precision:list/1/float, recall:list/1/float · returned float · level recorded 2026-09-24
cal_precision_recall_mae misc.py ran MIT (permissive) · d31192c9faa032ba · report fixture: signature prediction:ndarray/2/int, gt:ndarray/2/int · returned tuple · level recorded 2026-09-24
calc_precision_and_jaccard tools.py ran MIT (permissive) · e0f66060ff14683c · report fixture: signature pred:ndarray/2/float, gt:ndarray/2/float, th:float/0/float · returned tuple · level recorded 2026-09-24
cls_modulation_branch model_image.py ran MIT (permissive) · f3de7abdbee03ebc · report fixture: signature in_channel:int/0/int, hiden_channel:int/0/int · returned Sequential · level recorded 2026-09-24
generate_binary_map tools.py ran MIT (permissive) · 538d5931620a465b · report fixture: signature pred:ndarray/2/float, type:str/0/str, th:float/0/float · returned ndarray · level recorded 2026-09-24
hsp model_image.py ran MIT (permissive) · a72015580babe1d1 · report fixture: signature in_channel:int/0/int, out_channel:int/0/int · returned Sequential · level recorded 2026-09-24
img_normalize data_processed.py ran MIT (permissive) · e35f627f91cfd0df · report fixture: signature image:ndarray/2/float · returned ndarray · level recorded 2026-09-24
index_points in 49 papers Intra_MLP.py ran MIT (permissive) · 8301a9d5dbc96a5b · report fixture: signature device:str/0/str, points:Tensor/3/float, idx:Tensor/2/int · returned Tensor · level recorded 2026-09-24
knn_l2 Intra_MLP.py ran MIT (permissive) · 4e5ea5f4f33f1db3 · report fixture: signature device:str/0/str, net:Tensor/3/float, k:int/0/int, u:int/0/int · returned Tensor · level recorded 2026-09-24
pix_idx demo_matching.py ran fingerprinted MIT (permissive) · b3ea62a04ba82560 · report fixture: signature ii:int/0/int, jj:int/0/int · returned tuple · level recorded 2026-09-24
vgg in 16 papers model_image.py ran MIT (permissive) · 836db4ac2f48034c · report fixture: signature cfg:list/1/int, i:int/0/int, batch_norm:bool/0/bool · returned list · level recorded 2026-09-24
filt_small_instance data_processed.py unverified MIT (permissive) · 84645a1ce9d31efc · report

Tasks

Co-Salient Object DetectionObject DetectionSaliency DetectionSalient Object DetectionSemantic SegmentationVideo Salient Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Co-Salient Object Detection CoCA UFO MAE 0.095 #4 of 10 Archive leaderboard report
Co-Salient Object Detection CoCA UFO Mean F-measure 0.555 #4 of 10 Archive leaderboard report
Co-Salient Object Detection CoCA UFO S-measure 0.697 #4 of 10 Archive leaderboard report
Co-Salient Object Detection CoCA UFO max E-measure 0.782 #4 of 10 Archive leaderboard report
Co-Salient Object Detection CoCA UFO max F-measure 0.571 #4 of 10 Archive leaderboard report
Co-Salient Object Detection CoCA UFO mean E-measure 0.762 #4 of 10 Archive leaderboard report
Co-Salient Object Detection CoSOD3k UFO MAE 0.073 #3 of 10 Archive leaderboard report
Co-Salient Object Detection CoSOD3k UFO S-measure 0.819 #3 of 10 Archive leaderboard report
Co-Salient Object Detection CoSOD3k UFO max E-measure 0.874 #3 of 10 Archive leaderboard report
Co-Salient Object Detection CoSOD3k UFO max F-measure 0.797 #3 of 10 Archive leaderboard report
Co-Salient Object Detection CoSOD3k UFO mean E-measure 0.855 #3 of 10 Archive leaderboard report
Co-Salient Object Detection CoSOD3k UFO mean F-measure 0.783 #3 of 10 Archive leaderboard report
Co-Salient Object Detection CoSal2015 UFO MAE 0.064 #4 of 10 Archive leaderboard report
Co-Salient Object Detection CoSal2015 UFO S-measure 0.860 #4 of 10 Archive leaderboard report
Co-Salient Object Detection CoSal2015 UFO max E-measure 0.906 #4 of 10 Archive leaderboard report
Co-Salient Object Detection CoSal2015 UFO max F-measure 0.865 #4 of 10 Archive leaderboard report
Co-Salient Object Detection CoSal2015 UFO mean E-measure 0.889 #4 of 10 Archive leaderboard report
Co-Salient Object Detection CoSal2015 UFO mean F-measure 0.848 #4 of 10 Archive leaderboard report
Co-Salient Object Detection iCoSeg UFO MAE 0.029 #1 of 2 Archive leaderboard report
Co-Salient Object Detection iCoSeg UFO S-measure 0.924 #1 of 2 Archive leaderboard report
Co-Salient Object Detection iCoSeg UFO max E-measure 0.969 #1 of 2 Archive leaderboard report
Co-Salient Object Detection iCoSeg UFO max F-measure 0.953 #1 of 2 Archive leaderboard report
Video Salient Object Detection DAVIS-2016 UFO AVERAGE MAE 0.015 #2 of 11 Archive leaderboard report
Video Salient Object Detection DAVIS-2016 UFO MAX F-MEASURE 0.906 #2 of 11 Archive leaderboard report
Video Salient Object Detection DAVIS-2016 UFO S-Measure 0.918 #2 of 11 Archive leaderboard report
Video Salient Object Detection FBMS-59 UFO AVERAGE MAE 0.028 #2 of 16 Archive leaderboard report
Video Salient Object Detection FBMS-59 UFO MAX F-MEASURE 0.890 #2 of 16 Archive leaderboard report
Video Salient Object Detection FBMS-59 UFO S-Measure 0.894 #2 of 16 Archive leaderboard report
Video Salient Object Detection SegTrack v2 UFO AVERAGE MAE 0.022 #1 of 8 Archive leaderboard report
Video Salient Object Detection SegTrack v2 UFO MAX F-MEASURE 0.863 #1 of 8 Archive leaderboard report
Video Salient Object Detection SegTrack v2 UFO S-Measure 0.892 #1 of 8 Archive leaderboard report
Video Salient Object Detection ViSal UFO Average MAE 0.011 #2 of 10 Archive leaderboard report
Video Salient Object Detection ViSal UFO S-Measure 0.953 #2 of 10 Archive leaderboard report
Video Salient Object Detection ViSal UFO max E-measure 0.987 #2 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

SPEED

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