Papers › Make One-Shot Video Object Segmentation Efficient Again

Make One-Shot Video Object Segmentation Efficient Again

3 Dec 2020NeurIPS 2020 12arXiv:2012.01866archive 2025-07-28

Tim Meinhardt, Laura Leal-Taixe

Video object segmentation (VOS) describes the task of segmenting a set of objects in each frame of a video. In the semi-supervised setting, the first mask of each object is provided at test time. Following the one-shot principle, fine-tuning VOS methods train a segmentation model separately on each given object mask. However, recently the VOS community has deemed such a test time optimization and its impact on the test runtime as unfeasible. To mitigate the inefficiencies of previous fine-tuning approaches, we present efficient One-Shot Video Object Segmentation (e-OSVOS). In contrast to most VOS approaches, e-OSVOS decouples the object detection task and predicts only local segmentation masks by applying a modified version of Mask R-CNN. The one-shot test runtime and performance are optimized without a laborious and handcrafted hyperparameter search. To this end, we meta learn the model initialization and learning rates for the test time optimization. To achieve optimal learning behavior, we predict individual learning rates at a neuron level. Furthermore, we apply an online adaptation to address the common performance degradation throughout a sequence by continuously fine-tuning the model on previous mask predictions supported by a frame-to-frame bounding box propagation. e-OSVOS provides state-of-the-art results on DAVIS 2016, DAVIS 2017, and YouTube-VOS for one-shot fine-tuning methods while reducing the test runtime substantially. Code is available at https://github.com/dvl-tum/e-osvos.

PaperPDFConference PDFCode

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

dvl-tum/e-osvos officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
acaelles97/devis mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DeVIS: Making Deformable Transformers Work for Video Instance Segmentation (arXiv:2207.11103; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
timmeinhardt/trackformer mentioned on GitHubpytorchSyntology: not harvested report
MindSpore-paper-code-2/code2 mindsporeSyntology: not harvested 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

ObjectObject DetectionOne-shot visual object segmentationSegmentationSemantic SegmentationSemi-Supervised Video Object SegmentationVideo Object SegmentationVideo Semantic Segmentationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Video Object Segmentation DAVIS 2016 e-OSVOS F-measure (Mean) 87.0 #44 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 e-OSVOS J&F 86.8 #44 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 e-OSVOS Jaccard (Decay) 4.5 #44 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 e-OSVOS Jaccard (Mean) 86.6 #44 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) e-OSVOS F-measure (Mean) 68.6 #45 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) e-OSVOS J&F 64.8 #45 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) e-OSVOS Jaccard (Decay) 22.1 #45 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) e-OSVOS Jaccard (Mean) 60.9 #45 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) e-OSVOS F-measure (Mean) 80.0 #52 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) e-OSVOS J&F 77.2 #52 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) e-OSVOS Jaccard (Decay) 13.0 #52 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) e-OSVOS Jaccard (Mean) 74.4 #52 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 e-OSVOS F-Measure (Seen) 66.0 #43 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 e-OSVOS F-Measure (Unseen) 73.8 #43 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 e-OSVOS Jaccard (Seen) 71.7 #43 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 e-OSVOS Jaccard (Unseen) 74.3 #43 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 e-OSVOS Overall 71.4 #43 of 53 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

ConvolutionMask R-CNNRPNRoIAlignSoftmaxVOS

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