Papers › MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training

MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training

3 Aug 2022arXiv:2208.02245archive 2025-07-28

De-An Huang, Zhiding Yu, Anima Anandkumar

We propose MinVIS, a minimal video instance segmentation (VIS) framework that achieves state-of-the-art VIS performance with neither video-based architectures nor training procedures. By only training a query-based image instance segmentation model, MinVIS outperforms the previous best result on the challenging Occluded VIS dataset by over 10% AP. Since MinVIS treats frames in training videos as independent images, we can drastically sub-sample the annotated frames in training videos without any modifications. With only 1% of labeled frames, MinVIS outperforms or is comparable to fully-supervised state-of-the-art approaches on YouTube-VIS 2019/2021. Our key observation is that queries trained to be discriminative between intra-frame object instances are temporally consistent and can be used to track instances without any manually designed heuristics. MinVIS thus has the following inference pipeline: we first apply the trained query-based image instance segmentation to video frames independently. The segmented instances are then tracked by bipartite matching of the corresponding queries. This inference is done in an online fashion and does not need to process the whole video at once. MinVIS thus has the practical advantages of reducing both the labeling costs and the memory requirements, while not sacrificing the VIS performance. Code is available at: https://github.com/NVlabs/MinVIS

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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

nvlabs/minvis officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
kimhanjung/visage mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to id 01071 (not an arXiv id) (that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Instance SegmentationSegmentationSemantic SegmentationVideo Instance Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Instance Segmentation OVIS validation MinVIS (Swin-L) AP50 61.5 #21 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation MinVIS (Swin-L) AP75 41.3 #21 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation MinVIS (Swin-L) AR1 18.1 #21 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation MinVIS (Swin-L) AR10 43.3 #21 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation MinVIS (Swin-L) mask AP 39.4 #21 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 MinVIS (Swin-L) AP50 76.6 #16 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 MinVIS (Swin-L) AP75 62 #16 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 MinVIS (Swin-L) AR1 45.9 #16 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 MinVIS (Swin-L) AR10 60.8 #16 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 MinVIS (Swin-L) mask AP 55.3 #16 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation MinVIS (Swin-L) AP50 83.3 #5 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation MinVIS (Swin-L) AP75 68.6 #5 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation MinVIS (Swin-L) AR1 54.8 #5 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation MinVIS (Swin-L) AR10 66.6 #5 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation MinVIS (Swin-L) mask AP 61.6 #5 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