Papers › RefineVIS: Video Instance Segmentation with Temporal Attention Refinement

RefineVIS: Video Instance Segmentation with Temporal Attention Refinement

7 Jun 2023arXiv:2306.04774archive 2025-07-28

Andre Abrantes, Jiang Wang, Peng Chu, Quanzeng You, Zicheng Liu

We introduce a novel framework called RefineVIS for Video Instance Segmentation (VIS) that achieves good object association between frames and accurate segmentation masks by iteratively refining the representations using sequence context. RefineVIS learns two separate representations on top of an off-the-shelf frame-level image instance segmentation model: an association representation responsible for associating objects across frames and a segmentation representation that produces accurate segmentation masks. Contrastive learning is utilized to learn temporally stable association representations. A Temporal Attention Refinement (TAR) module learns discriminative segmentation representations by exploiting temporal relationships and a novel temporal contrastive denoising technique. Our method supports both online and offline inference. It achieves state-of-the-art video instance segmentation accuracy on YouTube-VIS 2019 (64.4 AP), Youtube-VIS 2021 (61.4 AP), and OVIS (46.1 AP) datasets. The visualization shows that the TAR module can generate more accurate instance segmentation masks, particularly for challenging cases such as highly occluded objects.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Contrastive LearningDenoisingInstance SegmentationSegmentationTARVideo Instance Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Instance Segmentation OVIS validation RefineVIS (Swin-L, offline) AP50 70.4 #10 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation RefineVIS (Swin-L, offline) AP75 48.4 #10 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation RefineVIS (Swin-L, offline) AR1 19.1 #10 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation RefineVIS (Swin-L, offline) AR10 51.2 #10 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation RefineVIS (Swin-L, offline) mask AP 46 #10 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 RefineVIS (Swin-L, online) AP50 84.1 #5 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 RefineVIS (Swin-L, online) AP75 68.5 #5 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 RefineVIS (Swin-L, online) AR1 48.3 #5 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 RefineVIS (Swin-L, online) AR10 65.2 #5 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 RefineVIS (Swin-L, online) mask AP 61.4 #5 of 26 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