Papers › General Object Foundation Model for Images and Videos at Scale

General Object Foundation Model for Images and Videos at Scale

14 Dec 2023CVPR 2024 1arXiv:2312.09158archive 2025-07-28

Junfeng Wu, Yi Jiang, Qihao Liu, Zehuan Yuan, Xiang Bai, Song Bai

We present GLEE in this work, an object-level foundation model for locating and identifying objects in images and videos. Through a unified framework, GLEE accomplishes detection, segmentation, tracking, grounding, and identification of arbitrary objects in the open world scenario for various object perception tasks. Adopting a cohesive learning strategy, GLEE acquires knowledge from diverse data sources with varying supervision levels to formulate general object representations, excelling in zero-shot transfer to new data and tasks. Specifically, we employ an image encoder, text encoder, and visual prompter to handle multi-modal inputs, enabling to simultaneously solve various object-centric downstream tasks while maintaining state-of-the-art performance. Demonstrated through extensive training on over five million images from diverse benchmarks, GLEE exhibits remarkable versatility and improved generalization performance, efficiently tackling downstream tasks without the need for task-specific adaptation. By integrating large volumes of automatically labeled data, we further enhance its zero-shot generalization capabilities. Additionally, GLEE is capable of being integrated into Large Language Models, serving as a foundational model to provide universal object-level information for multi-modal tasks. We hope that the versatility and universality of our method will mark a significant step in the development of efficient visual foundation models for AGI systems. The model and code will be released at https://glee-vision.github.io .

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 13 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 9 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 11 ran (2 with no instrument failure; 9 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 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 11 samples that ran has no recorded date.

FoundationVision/GLEE officialmentioned on GitHubpytorchMITSyntology: 13 samples, 11 ran (9 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

13 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 9 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

8ran · our draft was wrong
1ran; the contract check could not run
2ran
2unverified

Licence: 3 of the 13 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 FoundationVision/GLEE. “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.

FoundationVision/GLEE official repository 13 samples, 11 ran (9 instrument-failed) · 2 unverified
agg_lang_feat projects/GLEE/glee/models/glee_model.py ran MIT (permissive) here; the stored copy is pointer only · 95771c1a2d8346b7 · report fixture: signature features:Tensor/3/float, mask:Tensor/2/int, pool_type:str/0/str · returned Tensor · level recorded 2026-09-24
aligned_bilinear in 17 papers projects/GLEE/glee/models/vos_utils.py ran · our draft was wrong fingerprinted MIT (permissive) · 29dbbaafa4be18e1 · report fixture: signature tensor:Tensor/4/float, factor:int/0/int · returned Tensor · level recorded 2026-09-22
batch_dice_loss in 60 papers projects/GLEE/glee/models/matcher.py ran · our draft was wrong fingerprinted MIT (permissive) · bc2cb481a75c370d · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float · returned Tensor · level recorded 2026-09-25
dice_loss in 193 papers
census: 10 implementations from 16 papers, 7 distinct outputs across 4 buckets, one shared input per bucket
projects/GLEE/glee/models/criterion.py ran · our draft was wrong fingerprinted MIT (permissive) · 89f75e54ff128be0 · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_masks:float/0/float · returned Tensor · level recorded 2026-09-25
generate_regular_grid_point_coords projects/GLEE/glee/modules/point_features.py ran MIT (permissive) · 42ab1750d0229462 · report fixture: signature R:int/0/int, side_size:int/0/int, device:device/0/? · returned Tensor · level recorded 2026-09-24
load_opt_from_config_files projects/GLEE/train_net.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 670bf62deb1d06af · report fixture: signature conf_file:str/0/str · returned dict · level recorded 2026-09-24
masks_to_boxes in 5 papers projects/GLEE/glee/models/vos_utils.py ran · our draft was wrong fingerprinted MIT (permissive) · 3e759ab7f3a7de8d · report fixture: signature masks:Tensor/3/float · returned Tensor · level recorded 2026-09-24
point_sample in 12 papers projects/GLEE/glee/modules/point_features.py ran · our draft was wrong MIT (permissive) · 39e4af93b70bcddf · report fixture: signature input:Tensor/4/float, point_coords:Tensor/3/float · returned Tensor · level recorded 2026-09-24
rand_sample in 5 papers projects/GLEE/glee/models/glee_model.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) here; the stored copy is pointer only · 130323eef819c472 · report fixture: signature x:Tensor/2/float, max_len:int/0/int · returned Tensor · level recorded 2026-09-24
sigmoid_ce_loss in 70 papers
census: 4 implementations from 8 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
projects/GLEE/glee/models/criterion.py ran · our draft was wrong fingerprinted MIT (permissive) · d0c61e8dba511aa3 · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_masks:float/0/float · returned Tensor · level recorded 2026-09-25
sigmoid_focal_loss in 122 papers
census: 3 implementations from 9 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
projects/GLEE/glee/models/criterion.py ran · our draft was wrong fingerprinted MIT (permissive) · 5c0711aada67957e · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_boxes:int/0/int, alpha:float/0/float, gamma:float/0/float · returned Tensor · level recorded, date not recorded
batch_sigmoid_ce_loss in 48 papers projects/GLEE/glee/models/matcher.py unverified MIT (permissive) · 1edd24985036b0bf · report
multi_head_attention_forward in 73 papers projects/GLEE/glee/modules/attention.py unverified MIT (permissive) · 22a94fc69aed9aca · report

Tasks

Instance SegmentationLong-tail Video Object SegmentationMulti-Object TrackingObjectObject DetectionOpen-World Instance SegmentationReferring Expression ComprehensionReferring Expression SegmentationReferring Video Object SegmentationVideo Instance SegmentationVideo Object SegmentationZero-shot Generalization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation COCO minival GLEE-Pro mask AP 54.2 #8 of 93 Archive leaderboard report
Instance Segmentation COCO minival GLEE-Plus mask AP 53.0 #11 of 93 Archive leaderboard report
Instance Segmentation COCO minival GLEE-Lite mask AP 48.4 #37 of 93 Archive leaderboard report
Instance Segmentation COCO test-dev GLEE-Pro mask AP 54.5 #9 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev GLEE-Plus mask AP 53.3 #11 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev GLEE-Lite mask AP 48.3 #31 of 112 Archive leaderboard report
Instance Segmentation LVIS v1.0 val GLEE-Pro mask AP 49.9 #4 of 25 Archive leaderboard report
Long-tail Video Object Segmentation BURST GLEE-Lite HOTA (all) 22.6 #1 of 1 Archive leaderboard report
Long-tail Video Object Segmentation BURST GLEE-Lite HOTA (com) 36.4 #1 of 1 Archive leaderboard report
Long-tail Video Object Segmentation BURST GLEE-Lite HOTA (unc) 19.1 #1 of 1 Archive leaderboard report
Long-tail Video Object Segmentation BURST GLEE-Lite mAP (all) 12.6 #1 of 1 Archive leaderboard report
Long-tail Video Object Segmentation BURST GLEE-Lite mAP (com) 18.9 #1 of 1 Archive leaderboard report
Long-tail Video Object Segmentation BURST GLEE-Lite mAP (unc) 11.0 #1 of 1 Archive leaderboard report
Long-tail Video Object Segmentation BURST-val GLEE-Pro HOTA (all) 31.2 #1 of 5 Archive leaderboard report
Long-tail Video Object Segmentation BURST-val GLEE-Pro HOTA (com) 48.7 #1 of 5 Archive leaderboard report
Long-tail Video Object Segmentation BURST-val GLEE-Pro HOTA (unc) 26.9 #1 of 5 Archive leaderboard report
Long-tail Video Object Segmentation BURST-val GLEE-Pro mAP (all) 19.2 #1 of 5 Archive leaderboard report
Long-tail Video Object Segmentation BURST-val GLEE-Pro mAP (com) 24.8 #1 of 5 Archive leaderboard report
Long-tail Video Object Segmentation BURST-val GLEE-Pro mAP (unc) 17.7 #1 of 5 Archive leaderboard report
Long-tail Video Object Segmentation BURST-val GLEE-Plus HOTA (all) 26.9 #2 of 5 Archive leaderboard report
Long-tail Video Object Segmentation BURST-val GLEE-Plus HOTA (com) 38.8 #2 of 5 Archive leaderboard report
Long-tail Video Object Segmentation BURST-val GLEE-Plus HOTA (unc) 23.9 #2 of 5 Archive leaderboard report
Long-tail Video Object Segmentation BURST-val GLEE-Plus mAP (all) 17.2 #2 of 5 Archive leaderboard report
Long-tail Video Object Segmentation BURST-val GLEE-Plus mAP (com) 23.7 #2 of 5 Archive leaderboard report
Long-tail Video Object Segmentation BURST-val GLEE-Plus mAP (unc) 15.5 #2 of 5 Archive leaderboard report
Long-tail Video Object Segmentation BURST-val GLEE-Lite HOTA (all) 22.6 #3 of 5 Archive leaderboard report
Long-tail Video Object Segmentation BURST-val GLEE-Lite HOTA (com) 36.4 #3 of 5 Archive leaderboard report
Long-tail Video Object Segmentation BURST-val GLEE-Lite HOTA (unc) 19.1 #3 of 5 Archive leaderboard report
Long-tail Video Object Segmentation BURST-val GLEE-Lite mAP (all) 12.6 #3 of 5 Archive leaderboard report
Long-tail Video Object Segmentation BURST-val GLEE-Lite mAP (com) 18.9 #3 of 5 Archive leaderboard report
Long-tail Video Object Segmentation BURST-val GLEE-Lite mAP (unc) 11.0 #3 of 5 Archive leaderboard report
Multi-Object Tracking TAO GLEE-Pro AssocA 46.2 #2 of 9 Archive leaderboard report
Multi-Object Tracking TAO GLEE-Pro ClsA 29.1 #2 of 9 Archive leaderboard report
Multi-Object Tracking TAO GLEE-Pro LocA 66.2 #2 of 9 Archive leaderboard report
Multi-Object Tracking TAO GLEE-Pro TETA 47.2 #2 of 9 Archive leaderboard report
Multi-Object Tracking TAO GLEE-Plus AssocA 40.9 #3 of 9 Archive leaderboard report
Multi-Object Tracking TAO GLEE-Plus ClsA 30.8 #3 of 9 Archive leaderboard report
Multi-Object Tracking TAO GLEE-Plus LocA 52.9 #3 of 9 Archive leaderboard report
Multi-Object Tracking TAO GLEE-Plus TETA 41.5 #3 of 9 Archive leaderboard report
Multi-Object Tracking TAO GLEE-Lite AssocA 39.9 #4 of 9 Archive leaderboard report
Multi-Object Tracking TAO GLEE-Lite ClsA 24.1 #4 of 9 Archive leaderboard report
Multi-Object Tracking TAO GLEE-Lite LocA 56.3 #4 of 9 Archive leaderboard report
Multi-Object Tracking TAO GLEE-Lite TETA 40.1 #4 of 9 Archive leaderboard report
Object Detection COCO minival GLEE-Pro box AP 62.0 #17 of 220 Archive leaderboard report
Object Detection COCO minival GLEE-Plus box AP 60.4 #24 of 220 Archive leaderboard report
Object Detection COCO minival GLEE-Lite box AP 55.0 #53 of 220 Archive leaderboard report
Object Detection COCO test-dev GLEE-Pro box mAP 62.3 #22 of 225 Archive leaderboard report
Object Detection COCO test-dev GLEE-Plus box mAP 60.6 #27 of 225 Archive leaderboard report
Object Detection COCO test-dev GLEE-Lite box mAP 54.7 #54 of 225 Archive leaderboard report
Object Detection LVIS v1.0 val GLEE-Pro box AP 55.7 #6 of 15 Archive leaderboard report
Open-World Instance Segmentation UVO GLEE-Pro ARmask 72.6 #1 of 2 Archive leaderboard report
Referring Expression Segmentation RefCOCO GLEE-Pro IoU 80.0 #2 of 4 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ val GLEE-Pro Overall IoU 69.6 #15 of 33 Archive leaderboard report
Referring Expression Segmentation RefCOCOg-val GLEE-Pro Overall IoU 72.9 #10 of 23 Archive leaderboard report
Referring Expression Segmentation RefCoCo val GLEE-Pro Overall IoU 80.0 #11 of 37 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) GLEE-Pro F 72.9 #3 of 33 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) GLEE-Pro J 68.2 #3 of 33 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) GLEE-Pro J&F 70.6 #3 of 33 Archive leaderboard report
Referring Video Object Segmentation Refer-YouTube-VOS GLEE-Pro F 72.9 #2 of 18 Archive leaderboard report
Referring Video Object Segmentation Refer-YouTube-VOS GLEE-Pro J 68.2 #2 of 18 Archive leaderboard report
Referring Video Object Segmentation Refer-YouTube-VOS GLEE-Pro J&F 70.6 #2 of 18 Archive leaderboard report
Referring Video Object Segmentation Refer-YouTube-VOS GLEE-Plus F 69.7 #4 of 18 Archive leaderboard report
Referring Video Object Segmentation Refer-YouTube-VOS GLEE-Plus J 65.6 #4 of 18 Archive leaderboard report
Referring Video Object Segmentation Refer-YouTube-VOS GLEE-Plus J&F 67.7 #4 of 18 Archive leaderboard report
Video Instance Segmentation OVIS validation GLEE-Pro AP75 55.5 #4 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation GLEE-Pro mask AP 50.4 #4 of 44 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.

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