Papers › Collaborative Video Object Segmentation by Foreground-Background Integration

Collaborative Video Object Segmentation by Foreground-Background Integration

18 Mar 2020ECCV 2020 8arXiv:2003.08333archive 2025-07-28

Zongxin Yang, Yunchao Wei, Yi Yang

This paper investigates the principles of embedding learning to tackle the challenging semi-supervised video object segmentation. Different from previous practices that only explore the embedding learning using pixels from foreground object (s), we consider background should be equally treated and thus propose Collaborative video object segmentation by Foreground-Background Integration (CFBI) approach. Our CFBI implicitly imposes the feature embedding from the target foreground object and its corresponding background to be contrastive, promoting the segmentation results accordingly. With the feature embedding from both foreground and background, our CFBI performs the matching process between the reference and the predicted sequence from both pixel and instance levels, making the CFBI be robust to various object scales. We conduct extensive experiments on three popular benchmarks, i.e., DAVIS 2016, DAVIS 2017, and YouTube-VOS. Our CFBI achieves the performance (J$F) of 89.4%, 81.9%, and 81.4%, respectively, outperforming all the other state-of-the-art methods. Code: https://github.com/z-x-yang/CFBI.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

z-x-yang/CFBI officialmentioned in papermentioned on GitHubpytorchBSD-3-Clause 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

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

Tasks

ObjectOne-shot visual object segmentationSegmentationSemantic SegmentationSemi-Supervised Video Object SegmentationVideo Object SegmentationVideo Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) CFBI D16 val (F) 86.9 #10 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) CFBI D16 val (G) 86.1 #10 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) CFBI D16 val (J) 85.3 #10 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) CFBI D17 val (F) 77.7 #10 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) CFBI D17 val (G) 74.9 #10 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) CFBI D17 val (J) 72.1 #10 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) CFBI FPS 5.56 #10 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 CFBI F-measure (Mean) 90.5 #35 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 CFBI J&F 89.4 #35 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 CFBI Jaccard (Mean) 88.3 #35 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) CFBI F-measure (Mean) 78.5 #35 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) CFBI J&F 74.8 #35 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) CFBI Jaccard (Mean) 71.1 #35 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) CFBI F-measure (Mean) 84.6 #40 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) CFBI J&F 81.9 #40 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) CFBI Jaccard (Mean) 79.1 #40 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 CFBI F-Measure (Seen) 85.8 #38 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 CFBI F-Measure (Unseen) 83.4 #38 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 CFBI Jaccard (Seen) 81.1 #38 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 CFBI Jaccard (Unseen) 75.3 #38 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 CFBI Overall 81.4 #38 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 CFBI Params(M) 66.3 #38 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 CFBI Speed (FPS) 3.4 #38 of 53 Archive leaderboard report
Video Object Segmentation YouTube-VOS 2019 CFBI+ F-Measure (Seen) 86.2 #8 of 10 Archive leaderboard report
Video Object Segmentation YouTube-VOS 2019 CFBI+ F-Measure (Unseen) 85.2 #8 of 10 Archive leaderboard report
Video Object Segmentation YouTube-VOS 2019 CFBI+ Jaccard (Seen) 81.7 #8 of 10 Archive leaderboard report
Video Object Segmentation YouTube-VOS 2019 CFBI+ Jaccard (Unseen) 77.1 #8 of 10 Archive leaderboard report
Video Object Segmentation YouTube-VOS 2019 CFBI+ Mean Jaccard & F-Measure 82.6 #8 of 10 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