Papers › Video Mask Transfiner for High-Quality Video Instance Segmentation

Video Mask Transfiner for High-Quality Video Instance Segmentation

28 Jul 2022arXiv:2207.14012archive 2025-07-28

Lei Ke, Henghui Ding, Martin Danelljan, Yu-Wing Tai, Chi-Keung Tang, Fisher Yu

While Video Instance Segmentation (VIS) has seen rapid progress, current approaches struggle to predict high-quality masks with accurate boundary details. Moreover, the predicted segmentations often fluctuate over time, suggesting that temporal consistency cues are neglected or not fully utilized. In this paper, we set out to tackle these issues, with the aim of achieving highly detailed and more temporally stable mask predictions for VIS. We first propose the Video Mask Transfiner (VMT) method, capable of leveraging fine-grained high-resolution features thanks to a highly efficient video transformer structure. Our VMT detects and groups sparse error-prone spatio-temporal regions of each tracklet in the video segment, which are then refined using both local and instance-level cues. Second, we identify that the coarse boundary annotations of the popular YouTube-VIS dataset constitute a major limiting factor. Based on our VMT architecture, we therefore design an automated annotation refinement approach by iterative training and self-correction. To benchmark high-quality mask predictions for VIS, we introduce the HQ-YTVIS dataset, consisting of a manually re-annotated test set and our automatically refined training data. We compare VMT with the most recent state-of-the-art methods on the HQ-YTVIS, as well as the Youtube-VIS, OVIS and BDD100K MOTS benchmarks. Experimental results clearly demonstrate the efficacy and effectiveness of our method on segmenting complex and dynamic objects, by capturing precise details.

PaperPDFCodeCode Syntology ranMethod as code

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 7 code samples harvested from 1 repository linked to this paper: 5 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; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 7 samples from 1 repository, 5 ran (2 with no instrument failure; 3 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 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

SysCV/vmt mentioned on GitHubpytorchSyntology: 7 samples, 5 ran (3 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

7 samples harvested: 5 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; 3 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.

3ran · our draft was wrong
2ran
2unverified

Licence: 0 of the 7 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 SysCV/vmt. “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.

SysCV/vmt community (archive-listed) 7 samples, 5 ran (3 instrument-failed) · 2 unverified
TransformerEncoder in 96 papers models/segmentation.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 501c57cf59365f88 · report fixture: signature src:Tensor/3/float, pos:NoneType/0/? · returned Tensor · level recorded 2026-09-22
TransformerEncoderLayer in 90 papers models/segmentation.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · ed01e90c38f337c9 · report fixture: signature src:Tensor/3/float, pos:Tensor/3/float · returned Tensor · level recorded 2026-09-22
nested_tensor_from_tensor_list in 60 papers models/segmentation.py ran · our draft was wrong Apache-2.0 (permissive) · 27463d5407d3dddf · report fixture: signature tensor_list:list/1/Tensor, size_divisibility:int/0/int, split:bool/0/bool · returned NestedTensor · level recorded 2026-09-22
parse_dynamic_params in 14 papers models/segmentation.py ran · our draft was wrong Apache-2.0 (permissive) · 46f34dc9f9a94b67 · report fixture: signature params:Tensor/2/float, channels:int/0/int, weight_nums:list/1/int, bias_nums:list/1/int · returned tuple · level recorded 2026-09-22
pos_embed models/segmentation.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · ca652a3292b6646f · report fixture: signature x:Tensor/4/float, temperature:int/0/int, scale:float/0/float, normalize:bool/0/bool · returned Tensor · level recorded 2026-09-22
MaskHeadSmallConv models/segmentation.py unverified Apache-2.0 (permissive) · e3aeaa4531ba2770 · report
VMT models/segmentation.py unverified Apache-2.0 (permissive) · aa70e8fcfd59bba9 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Video Mask Transfiner (graph method: Video Mask Transfiner). 16 bricks; individually on a fixture: 13 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. VMT entry · level 0 · unverified · aa70e8fcfd59bba9
  2. MLP helper · level 1 · ran · 1630454d42cd8f1e
  3. MaskHeadSmallConv model · level 0 · unverified · e3aeaa4531ba2770
  4. NestedTensor helper · level 1 · ran · ace1b7ccab9cd45a
  5. TransformerEncoder model · level 1 · ran · 501c57cf59365f88
  6. TransformerEncoderLayer model · level 1 · ran · ed01e90c38f337c9
  7. aligned_bilinear helper · level 1 · ran · our draft was wrong · 29dbbaafa4be18e1
  8. compute_locations helper · level 1 · ran · honoured contract · ed1a308adb65f645
  9. inverse_sigmoid helper · level 1 · ran · our draft was wrong · 83c03ceb1307c6c4
  10. nested_tensor_from_tensor_list helper · level 1 · ran · our draft was wrong · 27463d5407d3dddf
  11. parse_dynamic_params helper · level 1 · ran · our draft was wrong · 46f34dc9f9a94b67
  12. pos_embed helper · level 1 · ran · our draft was wrong · ca652a3292b6646f
  13. _expand helper · level 0 · unverified · a104be81bc8116a7
  14. _get_clones helper · level 1 · ran · our draft was wrong · a8f1bbeb369e1829
  15. _get_activation_fn helper · level 1 · ran · our draft was wrong · 0bb264f52e707e08
  16. _max_by_axis helper · level 1 · ran · honoured contract · ef393284ce3c9ea1

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2207.14012") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Instance SegmentationSemantic SegmentationVideo Instance SegmentationVocal Bursts Intensity Prediction

Datasets

Introduced by this paper, per the archive.

HQ-YTVIS

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Instance Segmentation HQ-YTVIS VMT (Swin-L) Tube-Boundary AP 44.8 #1 of 4 Archive leaderboard report
Video Instance Segmentation HQ-YTVIS VMT (R101) Tube-Boundary AP 32.5 #3 of 4 Archive leaderboard report
Video Instance Segmentation HQ-YTVIS VMT (R50) Tube-Boundary AP 30.7 #4 of 4 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

Test

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