Papers › MOVE: Unsupervised Movable Object Segmentation and Detection

MOVE: Unsupervised Movable Object Segmentation and Detection

14 Oct 2022arXiv:2210.07920archive 2025-07-28

Adam Bielski, Paolo Favaro

We introduce MOVE, a novel method to segment objects without any form of supervision. MOVE exploits the fact that foreground objects can be shifted locally relative to their initial position and result in realistic (undistorted) new images. This property allows us to train a segmentation model on a dataset of images without annotation and to achieve state of the art (SotA) performance on several evaluation datasets for unsupervised salient object detection and segmentation. In unsupervised single object discovery, MOVE gives an average CorLoc improvement of 7.2% over the SotA, and in unsupervised class-agnostic object detection it gives a relative AP improvement of 53% on average. Our approach is built on top of self-supervised features (e.g. from DINO or MAE), an inpainting network (based on the Masked AutoEncoder) and adversarial training.

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="2210.07920")

Code

Syntology Ran 3 of 6 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · violated contract; 1 ran · fixture could not drive it; 1 ran with no contract checked.

By repository: official repository: 6 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.

adambielski/move-seg officialmentioned on GitHubpytorch 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

6 samples harvested; 3 ran; 0 honoured the contract we drafted; 3 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 · violated contract
1ran · fixture could not drive it
1ran
3unverified

Licence: 6 of the 6 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 adambielski/move-seg. “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.

MAEComposer adambielski/move-seg/segmenter.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · 0722135af9bb0f59 · report
compute_masks adambielski/move-seg/segmenter.py official repository ran · violated contract fingerprinted no licence file found · pointer only · 04caeb26969d90bb · report
unpatchify adambielski/move-seg/segmenter.py official repository ran · fixture could not drive it no licence file found · pointer only · 8b0381aa50dc096f · report
shift adambielski/move-seg/segmenter.py official repository unverified no licence file found · pointer only · a29acc562d4682ac · report
translate_outputs adambielski/move-seg/segmenter.py official repository unverified no licence file found · pointer only · a52a8e4c2617df93 · report
translation adambielski/move-seg/segmenter.py official repository unverified no licence file found · pointer only · b0ca28c88d618ac9 · report

Tasks

Class-agnostic Object DetectionObjectObject DetectionObject DiscoverySalient Object DetectionSegmentationSemantic SegmentationSingle-object discoveryUnsupervised Saliency Detectionobject-detection

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Single-object discovery COCO_20k MOVE + CAD CorLoc 71.9 #2 of 10 Archive leaderboard report
Single-object discovery COCO_20k MOVE CorLoc 66.6 #3 of 10 Archive leaderboard report
Unsupervised Saliency Detection DUT-OMRON MOVE Accuracy 93.7 #2 of 3 Archive leaderboard report
Unsupervised Saliency Detection DUT-OMRON MOVE IoU 66.6 #2 of 3 Archive leaderboard report
Unsupervised Saliency Detection DUT-OMRON MOVE maximal F-measure 76.6 #2 of 3 Archive leaderboard report
Unsupervised Saliency Detection DUTS MOVE Accuracy 95.4 #2 of 3 Archive leaderboard report
Unsupervised Saliency Detection DUTS MOVE IoU 72.8 #2 of 3 Archive leaderboard report
Unsupervised Saliency Detection DUTS MOVE maximal F-measure 82.9 #2 of 3 Archive leaderboard report
Unsupervised Saliency Detection ECSSD MOVE Accuracy 95.6 #2 of 3 Archive leaderboard report
Unsupervised Saliency Detection ECSSD MOVE IoU 83.6 #2 of 3 Archive leaderboard report
Unsupervised Saliency Detection ECSSD MOVE maximal F-measure 92.1 #2 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 ConnectionsInpaintingLayer 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