Papers › Unsupervised Object Localization: Observing the Background to Discover Objects

Unsupervised Object Localization: Observing the Background to Discover Objects

15 Dec 2022CVPR 2023 1arXiv:2212.07834archive 2025-07-28

Oriane Siméoni, Chloé Sekkat, Gilles Puy, Antonin Vobecky, Éloi Zablocki, Patrick Pérez

Recent advances in self-supervised visual representation learning have paved the way for unsupervised methods tackling tasks such as object discovery and instance segmentation. However, discovering objects in an image with no supervision is a very hard task; what are the desired objects, when to separate them into parts, how many are there, and of what classes? The answers to these questions depend on the tasks and datasets of evaluation. In this work, we take a different approach and propose to look for the background instead. This way, the salient objects emerge as a by-product without any strong assumption on what an object should be. We propose FOUND, a simple model made of a single conv1×1 initialized with coarse background masks extracted from self-supervised patch-based representations. After fast training and refining these seed masks, the model reaches state-of-the-art results on unsupervised saliency detection and object discovery benchmarks. Moreover, we show that our approach yields good results in the unsupervised semantic segmentation retrieval task. The code to reproduce our results is available at https://github.com/valeoai/FOUND.

PaperPDFConference PDFCodeCode 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 16 code samples harvested from 1 repository linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 16 samples from 1 repository, 14 ran (14 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 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

valeoai/found officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 16 samples, 14 ran (0 instrument-failed) · 2 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

16 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 2 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.

14ran
2unverified

Licence: 3 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 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 valeoai/found. “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.

valeoai/found official repository 16 samples, 14 ran (0 instrument-failed) · 2 unverified
IoU in 13 papers misc.py ran Apache-2.0 (permissive) · 83bbfbc25d284b4b · report fixture: signature mask1:Tensor/3/float, mask2:Tensor/3/float · returned float · level recorded 2026-09-25
compute_img_bkg_seg bkg_seg.py ran Apache-2.0 (permissive) · ad03beba02837819 · report fixture: signature attentions:Tensor/4/float, feats:Tensor/3/float, featmap_dims:tuple/1/int, th_bkg:float/0/float, dim:int/0/int, epsilon:float/0/float, apply_weights:bool/0/bool · returned Tensor · level recorded 2026-09-25
compute_size datasets/geometric_transforms.py ran Apache-2.0 (permissive) · 627a26cf332a1257 · report fixture: signature input_size:tuple/1/int, output_size:int/0/int, edge:str/0/str · returned tuple · level recorded 2026-09-25
create_gt_masks_if_voc datasets/VOC.py ran Apache-2.0 (permissive) · f6b0efb285e61b1f · report fixture: signature labels:Image/0/? · returned Image · level recorded 2026-09-25
extract_gt_COCO datasets/uod_datasets.py ran Apache-2.0 (permissive) · c0480f1a5fe8d95d · report fixture: signature targets:list/1/dict, remove_iscrowd:bool/0/bool · returned tuple · level recorded 2026-09-25
extract_gt_VOC datasets/uod_datasets.py ran Apache-2.0 (permissive) · b6b8ba6662e0aa6d · report fixture: signature targets:dict/0/?, remove_hards:bool/0/bool · returned tuple · level recorded 2026-09-25
get_valid_idx in 5 papers bilateral_solver.py ran fingerprinted Apache-2.0 (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
get_voc_detection_gt datasets/VOC.py ran Apache-2.0 (permissive) · 49d7f4f1978fcf07 · report fixture: signature metadata:dict/0/?, remove_hards:bool/0/bool · returned tuple · level recorded 2026-09-25
load_config in 389 papers misc.py ran Apache-2.0 (permissive) · d36a50450a39cb9f · report fixture: signature config_file:str/0/str · returned Struct · level recorded 2026-09-25
random_crop in 59 papers datasets/geometric_transforms.py ran Apache-2.0 (permissive) · cfbc0539d5d0564e · report fixture: signature image:Image/0/?, crop_size:tuple/1/int, fill:tuple/1/int, offset:tuple/1/int · returned tuple · level recorded 2026-09-25
resize in 108 papers
census: 10 implementations from 14 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
datasets/geometric_transforms.py ran Apache-2.0 (permissive) · 51da33e6dc962567 · report fixture: signature image:Image/0/?, size:int/0/int, interpolation:str/0/str, edge:str/0/str · returned Image · level recorded 2026-09-25
rgb2yuv bilateral_solver.py ran fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · ec22a04e890fb286 · report fixture: signature im:ndarray/3/float · returned ndarray · level recorded 2026-09-24
set_dataset_dir datasets/datasets.py ran Apache-2.0 (permissive) · 9ae96e58274012e3 · report fixture: signature dataset_name:str/0/str, root_dir:str/0/str · returned tuple · level recorded 2026-09-25
yuv2rgb in 5 papers bilateral_solver.py ran fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 5d9850cf710de517 · report fixture: signature im:ndarray/3/int · returned ndarray · level recorded 2026-09-24
create_VOC_loader datasets/VOC.py unverified Apache-2.0 (permissive) · 8c064d89722d29ff · report
discard_hard_voc datasets/uod_datasets.py unverified Apache-2.0 (permissive) · fac97e0bd4a7d7fd · report

Tasks

Instance SegmentationObjectObject DiscoveryObject LocalizationRepresentation LearningRetrievalSaliency DetectionSemantic SegmentationUnsupervised Object LocalizationUnsupervised Saliency DetectionUnsupervised Semantic Segmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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