Papers › Tracking Anything with Decoupled Video Segmentation

Tracking Anything with Decoupled Video Segmentation

7 Sep 2023ICCV 2023 1arXiv:2309.03903archive 2025-07-28

Ho Kei Cheng, Seoung Wug Oh, Brian Price, Alexander Schwing, Joon-Young Lee

Training data for video segmentation are expensive to annotate. This impedes extensions of end-to-end algorithms to new video segmentation tasks, especially in large-vocabulary settings. To 'track anything' without training on video data for every individual task, we develop a decoupled video segmentation approach (DEVA), composed of task-specific image-level segmentation and class/task-agnostic bi-directional temporal propagation. Due to this design, we only need an image-level model for the target task (which is cheaper to train) and a universal temporal propagation model which is trained once and generalizes across tasks. To effectively combine these two modules, we use bi-directional propagation for (semi-)online fusion of segmentation hypotheses from different frames to generate a coherent segmentation. We show that this decoupled formulation compares favorably to end-to-end approaches in several data-scarce tasks including large-vocabulary video panoptic segmentation, open-world video segmentation, referring video segmentation, and unsupervised video object segmentation. Code is available at: https://hkchengrex.github.io/Tracking-Anything-with-DEVA

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 10 code samples harvested from 1 repository linked to this paper: 7 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; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 10 samples from 1 repository, 7 ran (7 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

hkchengrex/Tracking-Anything-with-DEVA officialmentioned on GitHubpytorchNOASSERTIONSyntology: 10 samples, 7 ran (0 instrument-failed) · 3 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

10 samples harvested: 7 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; 0 where Syntology's instrument failed) · 3 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.

7ran
3unverified

Licence: 10 of the 10 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 hkchengrex/Tracking-Anything-with-DEVA. “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.

hkchengrex/Tracking-Anything-with-DEVA official repository 10 samples, 7 ran (0 instrument-failed) · 3 unverified
conv3x3 in 1,376 papers deva/model/resnet.py ran licence not identified · pointer only · 48f5a5ec1d5dd2ef · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, dilation:int/0/int · returned Conv2d · level recorded 2026-09-24
dice_loss in 193 papers
census: 10 implementations from 16 papers, 7 distinct outputs across 4 buckets, one shared input per bucket
deva/model/losses.py ran licence not identified · pointer only · 0d2e632209183345 · report fixture: signature input_mask:Tensor/4/float, cls_gt:Tensor/3/float · returned Tensor · level recorded 2026-09-24
do_softmax deva/model/memory_utils.py ran licence not identified · pointer only · b8e2bcf17a7d1985 · report fixture: signature similarity:Tensor/2/float, top_k:NoneType/0/?, inplace:bool/0/bool, return_usage:bool/0/bool · returned Tensor · level recorded 2026-09-24
downsample_groups in 5 papers deva/model/group_modules.py ran no licence file found · pointer only · 2048782602814ecb · report fixture: signature g:Tensor/4/float, ratio:float/0/float, mode:str/0/str, align_corners:NoneType/0/? · returned Tensor · level recorded 2026-09-24
get_similarity in 17 papers
census: 3 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
deva/model/memory_utils.py ran licence not identified · pointer only · 14cdff9c8a6cd96f · report fixture: signature mk:Tensor/3/float, ms:Tensor/2/float, qk:Tensor/3/float, qe:Tensor/3/float, add_batch_dim:bool/0/bool · returned Tensor · level recorded 2026-09-24
resnet18 in 432 papers deva/model/resnet.py ran licence not identified · pointer only · b4da85ddeff2a196 · report fixture: signature pretrained:bool/0/bool, extra_dim:int/0/int · returned ResNet · level recorded 2026-09-24
resnet50 in 121 papers deva/model/resnet.py ran licence not identified · pointer only · 0d0b892609b02b52 · report fixture: signature pretrained:bool/0/bool, extra_dim:int/0/int · returned ResNet · level recorded 2026-09-24
get_affinity in 5 papers deva/model/memory_utils.py unverified licence not identified · pointer only · 8185b445f454d15e · report
interpolate_groups in 5 papers deva/model/group_modules.py unverified no licence file found · pointer only · abf061dab6b3f9b9 · report
upsample_groups in 5 papers deva/model/group_modules.py unverified no licence file found · pointer only · 89405f8a57f3c3a5 · report

Tasks

Open-Vocabulary Video SegmentationOpen-World Video SegmentationPanoptic SegmentationReferring Expression SegmentationReferring Video Object SegmentationSegmentationSemantic SegmentationSemi-Supervised Video Object SegmentationUnsupervised Video Object SegmentationVideo Object SegmentationVideo Panoptic SegmentationVideo SegmentationVideo Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Open-World Video Segmentation BURST-val DEVA (Mask2Former) OWTA (all) 69.9 #1 of 3 Archive leaderboard report
Open-World Video Segmentation BURST-val DEVA (Mask2Former) OWTA (com) 75.2 #1 of 3 Archive leaderboard report
Open-World Video Segmentation BURST-val DEVA (Mask2Former) OWTA (unc) 41.5 #1 of 3 Archive leaderboard report
Open-World Video Segmentation BURST-val DEVA (EntitySeg) OWTA (all) 69.5 #2 of 3 Archive leaderboard report
Open-World Video Segmentation BURST-val DEVA (EntitySeg) OWTA (com) 73.3 #2 of 3 Archive leaderboard report
Open-World Video Segmentation BURST-val DEVA (EntitySeg) OWTA (unc) 50.5 #2 of 3 Archive leaderboard report
Referring Expression Segmentation DAVIS 2017 (val) DEVA (ReferFormer) J&F 1st frame 66.3 #3 of 18 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) DEVA (ReferFormer) J&F 66.0 #14 of 33 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) DEVA F-measure (Mean) 86.8 #8 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) DEVA FPS 25.3 #8 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) DEVA J&F 83.2 #8 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) DEVA Jaccard (Mean) 79.6 #8 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) DEVA F-measure (Mean) 91.0 #12 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) DEVA J&F 87.6 #12 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) DEVA Jaccard (Mean) 84.2 #12 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) DEVA Speed (FPS) 25.3 #12 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation MOSE DEVA (with OVIS) F 70.8 #8 of 17 Archive leaderboard report
Semi-Supervised Video Object Segmentation MOSE DEVA (with OVIS) FPS 25.3 #8 of 17 Archive leaderboard report
Semi-Supervised Video Object Segmentation MOSE DEVA (with OVIS) J 62.3 #8 of 17 Archive leaderboard report
Semi-Supervised Video Object Segmentation MOSE DEVA (with OVIS) J&F 66.5 #8 of 17 Archive leaderboard report
Semi-Supervised Video Object Segmentation MOSE DEVA (no OVIS) F 64.3 #11 of 17 Archive leaderboard report
Semi-Supervised Video Object Segmentation MOSE DEVA (no OVIS) FPS 25.3 #11 of 17 Archive leaderboard report
Semi-Supervised Video Object Segmentation MOSE DEVA (no OVIS) J 55.8 #11 of 17 Archive leaderboard report
Semi-Supervised Video Object Segmentation MOSE DEVA (no OVIS) J&F 60.0 #11 of 17 Archive leaderboard report
Unsupervised Video Object Segmentation DAVIS 2016 val DEVA (DIS) F 90.2 #2 of 25 Archive leaderboard report
Unsupervised Video Object Segmentation DAVIS 2016 val DEVA (DIS) G 88.9 #2 of 25 Archive leaderboard report
Unsupervised Video Object Segmentation DAVIS 2016 val DEVA (DIS) J 87.6 #2 of 25 Archive leaderboard report
Unsupervised Video Object Segmentation DAVIS 2017 (test-dev) DEVA (EntitySeg) J&F 62.1 #1 of 6 Archive leaderboard report
Unsupervised Video Object Segmentation DAVIS 2017 (val) DEVA (EntitySeg) F-measure (Mean) 76.4 #1 of 10 Archive leaderboard report
Unsupervised Video Object Segmentation DAVIS 2017 (val) DEVA (EntitySeg) J&F 73.4 #1 of 10 Archive leaderboard report
Unsupervised Video Object Segmentation DAVIS 2017 (val) DEVA (EntitySeg) Jaccard (Mean) 70.4 #1 of 10 Archive leaderboard report
Video Panoptic Segmentation VIPSeg DEVA (Mask2Former - SwinB) STQ 52.2 #6 of 12 Archive leaderboard report
Video Panoptic Segmentation VIPSeg DEVA (Mask2Former - SwinB) VPQ 55.0 #6 of 12 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