Papers › DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering

DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering

12 Dec 2022arXiv:2212.05853archive 2025-07-28

Amit Aflalo, Shai Bagon, Tamar Kashti, Yonina Eldar

Image segmentation is a fundamental task in computer vision. Data annotation for training supervised methods can be labor-intensive, motivating unsupervised methods. Current approaches often rely on extracting deep features from pre-trained networks to construct a graph, and classical clustering methods like k-means and normalized-cuts are then applied as a post-processing step. However, this approach reduces the high-dimensional information encoded in the features to pair-wise scalar affinities. To address this limitation, this study introduces a lightweight Graph Neural Network (GNN) to replace classical clustering methods while optimizing for the same clustering objective function. Unlike existing methods, our GNN takes both the pair-wise affinities between local image features and the raw features as input. This direct connection between the raw features and the clustering objective enables us to implicitly perform classification of the clusters between different graphs, resulting in part semantic segmentation without the need for additional post-processing steps. We demonstrate how classical clustering objectives can be formulated as self-supervised loss functions for training an image segmentation GNN. Furthermore, we employ the Correlation-Clustering (CC) objective to perform clustering without defining the number of clusters, allowing for k-less clustering. We apply the proposed method for object localization, segmentation, and semantic part segmentation tasks, surpassing state-of-the-art performance on multiple benchmarks.

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 8 code samples harvested from 1 repository linked to this paper: 8 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; 1 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 8 samples from 1 repository, 8 ran (7 with no instrument failure; 1 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 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 8 samples that ran has no recorded date.

sampl-weizmann/deepcut mentioned on GitHubpytorchMITSyntology: 8 samples, 8 ran (1 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

8 samples harvested: 8 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; 1 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; the contract check could not run
7ran

Licence: 4 of the 8 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 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 sampl-weizmann/deepcut. “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.

sampl-weizmann/deepcut community (archive-listed) 8 samples, 8 ran (1 instrument-failed) · 0 unverified
create_adj util.py ran fingerprinted MIT (permissive) · 57e7ea042721ced7 · report fixture: signature F:Tensor/2/float, cut:int/0/int, alpha:int/0/int · returned Tensor · level recorded 2026-09-25
deep_features features_extract.py ran MIT (permissive) · 97f05e1bca597f48 · report fixture: signature image_tensor:Tensor/3/float, extractor:callable/0/?, layer:int/0/int, facet:str/0/str, bin:bool/0/bool, include_cls:bool/0/bool, device:str/0/str · returned ndarray · level recorded 2026-09-25
discr_ncut util.py ran MIT (permissive) · 32039f99241f69da · report fixture: signature A:tuple/1/ndarray, B:tuple/1/ndarray, deg:ndarray/1/float, W:ndarray/2/float · returned float · level recorded 2026-09-25
drop_path in 325 papers
census: 27 implementations from 61 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 2, kind float, dtype float32
vision_transformer.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) here; the stored copy is pointer only · 55120f2026b56aa2 · report fixture: signature x:Tensor/2/float, drop_prob:float/0/float, training:bool/0/bool · returned Tensor · level recorded, date not recorded
get_valid_idx in 5 papers bilateral_solver.py ran fingerprinted MIT (permissive) here; the stored copy is pointer only · 04c4101fccb5c55b · report fixture: signature valid:ndarray/1/int, candidates:ndarray/1/int · returned tuple · level recorded 2026-09-24
graph_to_mask util.py ran MIT (permissive) · 8df1b6ec8f138441 · report fixture: signature S:Tensor/1/float, cc:bool/0/bool, stride:int/0/int, image_tensor:Tensor/4/float, image:ndarray/3/float · returned tuple · level recorded 2026-09-25
rgb2yuv bilateral_solver.py ran fingerprinted MIT (permissive) here; the stored copy is pointer only · ec22a04e890fb286 · report fixture: signature im:ndarray/3/float · returned ndarray · level recorded 2026-09-24
yuv2rgb in 5 papers bilateral_solver.py ran fingerprinted MIT (permissive) here; the stored copy is pointer only · 5d9850cf710de517 · report fixture: signature im:ndarray/3/int · returned ndarray · level recorded 2026-09-24

Tasks

ClusteringGraph Neural NetworkImage SegmentationObject LocalizationObject SegmentationSegmentationSemantic SegmentationUnsupervised Object LocalizationUnsupervised Object Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Object Localization COCO_20k DeepCut CorLoc 61.6 #1 of 1 Archive leaderboard report
Unsupervised Object Localization PASCAL VOC 2007 DeepCut CorLoc 69.8 #1 of 1 Archive leaderboard report
Unsupervised Object Localization PASCAL VOC 2012 DeepCut CorLoc 72.2 #1 of 1 Archive leaderboard report
Unsupervised Object Segmentation DUTS DeepCut mIoU 59.5 #1 of 1 Archive leaderboard report
Unsupervised Object Segmentation ECSSD DeepCut mIoU 74.6 #2 of 2 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

Graph Neural Network

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