Papers › Treating Motion as Option with Output Selection for Unsupervised Video Object Segmentation

Treating Motion as Option with Output Selection for Unsupervised Video Object Segmentation

26 Sep 2023arXiv:2309.14786archive 2025-07-28

Suhwan Cho, Minhyeok Lee, Jungho Lee, MyeongAh Cho, Sangyoun Lee

Unsupervised video object segmentation (VOS) is a task that aims to detect the most salient object in a video without external guidance about the object. To leverage the property that salient objects usually have distinctive movements compared to the background, recent methods collaboratively use motion cues extracted from optical flow maps with appearance cues extracted from RGB images. However, as optical flow maps are usually very relevant to segmentation masks, the network is easy to be learned overly dependent on the motion cues during network training. As a result, such two-stream approaches are vulnerable to confusing motion cues, making their prediction unstable. To relieve this issue, we design a novel motion-as-option network by treating motion cues as optional. During network training, RGB images are randomly provided to the motion encoder instead of optical flow maps, to implicitly reduce motion dependency of the network. As the learned motion encoder can deal with both RGB images and optical flow maps, two different predictions can be generated depending on which source information is used as motion input. In order to fully exploit this property, we also propose an adaptive output selection algorithm to adopt optimal prediction result at test time. Our proposed approach affords state-of-the-art performance on all public benchmark datasets, even maintaining real-time inference speed.

PaperPDFCode

Syntology This paper's arXiv id is not in Syntology's Atlas id list (549,449 ids, as this build read them; the read time is in the build record), so this page links to no Syntology page for it. The list is not the whole graph; Syntology's feed shows papers as they enter the graph.

Code

suhwan-cho/tmo officialmentioned in papermentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation (arXiv:2209.03138; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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

ObjectOptical Flow EstimationSemantic SegmentationUnsupervised Video Object SegmentationVideo Object SegmentationVideo Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Video Object Segmentation FBMS test TMO++ (MiT-b1) J 83.2 #3 of 15 Archive leaderboard report
Unsupervised Video Object Segmentation FBMS test TMO++ (RN-101) J 81.2 #5 of 15 Archive leaderboard report
Unsupervised Video Object Segmentation YouTube-Objects TMO++ (MiT-b1, MS) J 73.5 #4 of 16 Archive leaderboard report
Unsupervised Video Object Segmentation YouTube-Objects TMO++ (RN-101) J 73.1 #5 of 16 Archive leaderboard report
Unsupervised Video Object Segmentation YouTube-Objects TMO++ (MiT-b1) J 73.0 #6 of 16 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