Papers › Fast Video Object Segmentation by Reference-Guided Mask Propagation

Fast Video Object Segmentation by Reference-Guided Mask Propagation

1 Jun 2018CVPR 2018 6archive 2025-07-28

Seoung Wug Oh, Joon-Young Lee, Kalyan Sunkavalli, Seon Joo Kim

We present an efficient method for the semi-supervised video object segmentation. Our method achieves accuracy competitive with state-of-the-art methods while running in a fraction of time compared to others. To this end, we propose a deep Siamese encoder-decoder network that is designed to take advantage of mask propagation and object detection while avoiding the weaknesses of both approaches. Our network, learned through a two-stage training process that exploits both synthetic and real data, works robustly without any online learning or post-processing. We validate our method on four benchmark sets that cover single and multiple object segmentation. On all the benchmark sets, our method shows comparable accuracy while having the order of magnitude faster runtime. We also provide extensive ablation and add-on studies to analyze and evaluate our framework.

PaperPDFCode

Code

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

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

Tasks

DecoderObjectObject DetectionSegmentationSemantic SegmentationSemi-Supervised Video Object SegmentationVideo Object SegmentationVideo Semantic SegmentationVisual Object Trackingobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Video Object Segmentation DAVIS 2016 RGMP F-measure (Decay) 10.1 #57 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 RGMP F-measure (Mean) 82.0 #57 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 RGMP F-measure (Recall) 90.8 #57 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 RGMP J&F 81.75 #57 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 RGMP Jaccard (Decay) 10.9 #57 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 RGMP Jaccard (Mean) 81.5 #57 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 RGMP Jaccard (Recall) 91.7 #57 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) RGMP F-measure (Decay) 37.2 #51 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) RGMP F-measure (Mean) 54.4 #51 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) RGMP F-measure (Recall) 61.9 #51 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) RGMP J&F 52.8 #51 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) RGMP Jaccard (Decay) 34.3 #51 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) RGMP Jaccard (Mean) 51.3 #51 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) RGMP Jaccard (Recall) 59.0 #51 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) RGMP F-measure (Decay) 19.6 #64 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) RGMP F-measure (Mean) 68.6 #64 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) RGMP F-measure (Recall) 77.7 #64 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) RGMP J&F 66.7 #64 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) RGMP Jaccard (Decay) 18.9 #64 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) RGMP Jaccard (Mean) 64.8 #64 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) RGMP Jaccard (Recall) 74.1 #64 of 81 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