Papers › Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation
Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation
Yuxi Li, Ning Xu, Jinlong Peng, John See, Weiyao Lin
In this paper, we address several inadequacies of current video object segmentation pipelines. Firstly, a cyclic mechanism is incorporated to the standard semi-supervised process to produce more robust representations. By relying on the accurate reference mask in the starting frame, we show that the error propagation problem can be mitigated. Next, we introduce a simple gradient correction module, which extends the offline pipeline to an online method while maintaining the efficiency of the former. Finally we develop cycle effective receptive field (cycle-ERF) based on gradient correction to provide a new perspective into analyzing object-specific regions of interests. We conduct comprehensive experiments on challenging benchmarks of DAVIS17 and Youtube-VOS, demonstrating that the cyclic mechanism is beneficial to segmentation quality.
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.
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Semi-Supervised Video Object Segmentation | YouTube-VOS 2018 | STM-cycle | F-Measure (Seen) | 75.8 | #44 of 53 | Archive leaderboard | report |
| Semi-Supervised Video Object Segmentation | YouTube-VOS 2018 | STM-cycle | F-Measure (Unseen) | 70.4 | #44 of 53 | Archive leaderboard | report |
| Semi-Supervised Video Object Segmentation | YouTube-VOS 2018 | STM-cycle | Jaccard (Seen) | 71.7 | #44 of 53 | Archive leaderboard | report |
| Semi-Supervised Video Object Segmentation | YouTube-VOS 2018 | STM-cycle | Overall | 69.9 | #44 of 53 | Archive leaderboard | report |
| Semi-Supervised Video Object Segmentation | YouTube-VOS 2018 | STM-cycle | Speed (FPS) | 61.4 | #44 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.
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