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 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="2309.03903")

Code

Syntology Ran 7 of 10 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 7 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

hkchengrex/Tracking-Anything-with-DEVA officialmentioned on GitHubpytorchNOASSERTION 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; 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.

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. “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 hkchengrex/Tracking-Anything-with-DEVA/deva/model/resnet.py official repository ran licence not identified · pointer only · 48f5a5ec1d5dd2ef · report
dice_loss hkchengrex/Tracking-Anything-with-DEVA/deva/model/losses.py official repository ran licence not identified · pointer only · 0d2e632209183345 · report
do_softmax hkchengrex/Tracking-Anything-with-DEVA/deva/model/memory_utils.py official repository ran licence not identified · pointer only · b8e2bcf17a7d1985 · report
downsample_groups hkchengrex/Tracking-Anything-with-DEVA/deva/model/group_modules.py official repository ran no licence file found · pointer only · 2048782602814ecb · report
get_similarity hkchengrex/Tracking-Anything-with-DEVA/deva/model/memory_utils.py official repository ran licence not identified · pointer only · 14cdff9c8a6cd96f · report
resnet18 hkchengrex/Tracking-Anything-with-DEVA/deva/model/resnet.py official repository ran licence not identified · pointer only · b4da85ddeff2a196 · report
resnet50 hkchengrex/Tracking-Anything-with-DEVA/deva/model/resnet.py official repository ran licence not identified · pointer only · 0d0b892609b02b52 · report
get_affinity hkchengrex/Tracking-Anything-with-DEVA/deva/model/memory_utils.py official repository unverified licence not identified · pointer only · 8185b445f454d15e · report
interpolate_groups hkchengrex/Tracking-Anything-with-DEVA/deva/model/group_modules.py official repository unverified no licence file found · pointer only · abf061dab6b3f9b9 · report
upsample_groups hkchengrex/Tracking-Anything-with-DEVA/deva/model/group_modules.py official repository 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