Papers › Unsupervised Salient Object Detection with Spectral Cluster Voting

Unsupervised Salient Object Detection with Spectral Cluster Voting

23 Mar 2022arXiv:2203.12614archive 2025-07-28

Gyungin Shin, Samuel Albanie, Weidi Xie

In this paper, we tackle the challenging task of unsupervised salient object detection (SOD) by leveraging spectral clustering on self-supervised features. We make the following contributions: (i) We revisit spectral clustering and demonstrate its potential to group the pixels of salient objects; (ii) Given mask proposals from multiple applications of spectral clustering on image features computed from various self-supervised models, e.g., MoCov2, SwAV, DINO, we propose a simple but effective winner-takes-all voting mechanism for selecting the salient masks, leveraging object priors based on framing and distinctiveness; (iii) Using the selected object segmentation as pseudo groundtruth masks, we train a salient object detector, dubbed SelfMask, which outperforms prior approaches on three unsupervised SOD benchmarks. Code is publicly available at https://github.com/NoelShin/selfmask.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2203.12614")

Code

Syntology Ran 3 of 9 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 2 ran · fixture could not drive it.

By repository: official repository: 9 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

noelshin/selfmask officialmentioned in papermentioned on GitHubpytorchMIT 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

9 samples harvested; 3 ran; 0 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
2ran · fixture could not drive it
6unverified

Licence: 0 of the 9 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 noelshin/selfmask. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

conv3x3 noelshin/selfmask/networks/resnet_models.py official repository ran · our draft was wrong MIT (permissive) · fac5364e2f53c6db · report
drop_path noelshin/selfmask/networks/vision_transformer.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 55120f2026b56aa2 · report
trunc_normal_ noelshin/selfmask/networks/vision_transformer.py official repository ran · fixture could not drive it MIT (permissive) · 915b71e73a54fc97 · report
ResNetBackbone noelshin/selfmask/networks/resnet_backbone.py official repository unverified MIT (permissive) · 66e194b18f29f1f2 · report
checkpoint_filter_fn noelshin/selfmask/networks/timm_vit.py official repository unverified MIT (permissive) · 5dac11fdc41c896b · report
deepbase_resnet18 noelshin/selfmask/networks/resnet_models.py official repository unverified MIT (permissive) · 01b5be2b9eb52e62 · report
deit_tiny noelshin/selfmask/networks/vision_transformer.py official repository unverified MIT (permissive) · dded96f53fb5aeb2 · report
resize_pos_embed noelshin/selfmask/networks/timm_vit.py official repository unverified MIT (permissive) · 1dbef2d4da4ee10f · report
resnet18 noelshin/selfmask/networks/resnet_models.py official repository unverified MIT (permissive) · 11a05b824892ef2d · report

Tasks

ClusteringObjectObject DetectionSalient Object DetectionSemantic SegmentationUnsupervised Saliency Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Saliency Detection DUT-OMRON SelfMask Accuracy 91.9 #1 of 3 Archive leaderboard report
Unsupervised Saliency Detection DUT-OMRON SelfMask IoU 65.5 #1 of 3 Archive leaderboard report
Unsupervised Saliency Detection DUT-OMRON SelfMask maximal F-measure 85.2 #1 of 3 Archive leaderboard report
Unsupervised Saliency Detection DUTS SelfMask Accuracy 93.3 #1 of 3 Archive leaderboard report
Unsupervised Saliency Detection DUTS SelfMask IoU 66 #1 of 3 Archive leaderboard report
Unsupervised Saliency Detection DUTS SelfMask maximal F-measure 88.2 #1 of 3 Archive leaderboard report
Unsupervised Saliency Detection ECSSD SelfMask Accuracy 95.5 #1 of 3 Archive leaderboard report
Unsupervised Saliency Detection ECSSD SelfMask IoU 81.8 #1 of 3 Archive leaderboard report
Unsupervised Saliency Detection ECSSD SelfMask maximal F-measure 95.6 #1 of 3 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

AttentionDense ConnectionsLARSLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSoftmaxSpectral ClusteringSwAVVision 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