Papers › In Defense of Online Models for Video Instance Segmentation

In Defense of Online Models for Video Instance Segmentation

21 Jul 2022arXiv:2207.10661archive 2025-07-28

Junfeng Wu, Qihao Liu, Yi Jiang, Song Bai, Alan Yuille, Xiang Bai

In recent years, video instance segmentation (VIS) has been largely advanced by offline models, while online models gradually attracted less attention possibly due to their inferior performance. However, online methods have their inherent advantage in handling long video sequences and ongoing videos while offline models fail due to the limit of computational resources. Therefore, it would be highly desirable if online models can achieve comparable or even better performance than offline models. By dissecting current online models and offline models, we demonstrate that the main cause of the performance gap is the error-prone association between frames caused by the similar appearance among different instances in the feature space. Observing this, we propose an online framework based on contrastive learning that is able to learn more discriminative instance embeddings for association and fully exploit history information for stability. Despite its simplicity, our method outperforms all online and offline methods on three benchmarks. Specifically, we achieve 49.5 AP on YouTube-VIS 2019, a significant improvement of 13.2 AP and 2.1 AP over the prior online and offline art, respectively. Moreover, we achieve 30.2 AP on OVIS, a more challenging dataset with significant crowding and occlusions, surpassing the prior art by 14.8 AP. The proposed method won first place in the video instance segmentation track of the 4th Large-scale Video Object Segmentation Challenge (CVPR2022). We hope the simplicity and effectiveness of our method, as well as our insight into current methods, could shed light on the exploration of VIS models.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2207.10661")

Code

Syntology Ran 3 of 5 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: community (archive-listed): 5 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

wjf5203/vnext officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
mkimhi/RISE mentioned on GitHubpytorch 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

5 samples harvested; 3 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

2ran · our draft was wrong
1ran · fixture could not drive it
2unverified

Licence: 0 of the 5 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 mkimhi/RISE. “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.

dynamic_k_matching mkimhi/RISE/projects/RISE/rise/models/pos_neg_select.py community (archive-listed) ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 84ec806321d4d1db · report
generalized_box_iou mkimhi/RISE/projects/RISE/rise/models/pos_neg_select.py community (archive-listed) ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · d0ce32748ce099f4 · report
get_in_boxes_info mkimhi/RISE/projects/RISE/rise/models/pos_neg_select.py community (archive-listed) ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · c10508ee5ab04682 · report
get_pos_idx mkimhi/RISE/projects/RISE/rise/models/pos_neg_select.py community (archive-listed) unverified Apache-2.0 (permissive) · 801c3bc9596af85a · report
select_pos_neg mkimhi/RISE/projects/RISE/rise/models/pos_neg_select.py community (archive-listed) unverified Apache-2.0 (permissive) · 48e66a2981766770 · report

Tasks

Contrastive LearningInstance SegmentationSegmentationSemantic SegmentationVideo Instance SegmentationVideo Object SegmentationVideo Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Instance Segmentation OVIS validation IDOL (Swin-L) AP50 65.7 #16 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation IDOL (Swin-L) AP75 45.2 #16 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation IDOL (Swin-L) AR1 17.9 #16 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation IDOL (Swin-L) AR10 49.6 #16 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation IDOL (Swin-L) mask AP 42.6 #16 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation IDOL (ResNet-50) AP50 51.3 #30 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation IDOL (ResNet-50) AP75 30 #30 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation IDOL (ResNet-50) AR1 15 #30 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation IDOL (ResNet-50) AR10 37.5 #30 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation IDOL (ResNet-50) mask AP 30.2 #30 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 IDOL (Swin-L) AP50 80.8 #14 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 IDOL (Swin-L) AP75 63.5 #14 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 IDOL (Swin-L) AR1 45 #14 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 IDOL (Swin-L) AR10 60.1 #14 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 IDOL (Swin-L) mask AP 56.1 #14 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation IDOL (ResNet-50) AP50 74 #15 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation IDOL (ResNet-50) AP75 52.9 #15 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation IDOL (ResNet-50) AR1 47.7 #15 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation IDOL (ResNet-50) AR10 58.7 #15 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation IDOL (ResNet-50) mask AP 49.5 #15 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.

Methods

Contrastive Learning

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