Papers › Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping

Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping

17 Apr 2023CVPR 2023 1arXiv:2304.08025archive 2025-07-28

Long Lian, Zhirong Wu, Stella X. Yu

We study learning object segmentation from unlabeled videos. Humans can easily segment moving objects without knowing what they are. The Gestalt law of common fate, i.e., what move at the same speed belong together, has inspired unsupervised object discovery based on motion segmentation. However, common fate is not a reliable indicator of objectness: Parts of an articulated / deformable object may not move at the same speed, whereas shadows / reflections of an object always move with it but are not part of it. Our insight is to bootstrap objectness by first learning image features from relaxed common fate and then refining them based on visual appearance grouping within the image itself and across images statistically. Specifically, we learn an image segmenter first in the loop of approximating optical flow with constant segment flow plus small within-segment residual flow, and then by refining it for more coherent appearance and statistical figure-ground relevance. On unsupervised video object segmentation, using only ResNet and convolutional heads, our model surpasses the state-of-the-art by absolute gains of 7/9/5% on DAVIS16 / STv2 / FBMS59 respectively, demonstrating the effectiveness of our ideas. Our code is publicly available.

PaperPDFConference PDFCode

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

Code

TonyLianLong/RCF-UnsupVideoSeg officialmentioned on GitHubpytorchNOASSERTION 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

Motion SegmentationObjectObject DiscoveryOptical Flow EstimationSegmentationSemantic SegmentationUnsupervised Object SegmentationUnsupervised Video Object SegmentationVideo Object SegmentationVideo Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Object Segmentation DAVIS 2016 RCF (with Post-Processing) J score 83.0 #1 of 9 Archive leaderboard report
Unsupervised Object Segmentation DAVIS 2016 RCF (without Post-Processing) J score 80.9 #2 of 9 Archive leaderboard report
Unsupervised Object Segmentation FBMS-59 RCF (with post-processing) mIoU 72.4 #1 of 7 Archive leaderboard report
Unsupervised Object Segmentation FBMS-59 RCF (without post-processing) mIoU 69.9 #2 of 7 Archive leaderboard report
Unsupervised Object Segmentation SegTrack-v2 RCF (with post-processing) mIoU 79.6 #1 of 8 Archive leaderboard report
Unsupervised Object Segmentation SegTrack-v2 RCF (without post-processing) mIoU 76.7 #2 of 8 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

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual ConnectionSPEED

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