Papers › Adaptive Multi-source Predictor for Zero-shot Video Object Segmentation

Adaptive Multi-source Predictor for Zero-shot Video Object Segmentation

18 Mar 2023arXiv:2303.10383archive 2025-07-28

Xiaoqi Zhao, Shijie Chang, Youwei Pang, Jiaxing Yang, Lihe Zhang, Huchuan Lu

Static and moving objects often occur in real-life videos. Most video object segmentation methods only focus on extracting and exploiting motion cues to perceive moving objects. Once faced with the frames of static objects, the moving object predictors may predict failed results caused by uncertain motion information, such as low-quality optical flow maps. Besides, different sources such as RGB, depth, optical flow and static saliency can provide useful information about the objects. However, existing approaches only consider either the RGB or RGB and optical flow. In this paper, we propose a novel adaptive multi-source predictor for zero-shot video object segmentation (ZVOS). In the static object predictor, the RGB source is converted to depth and static saliency sources, simultaneously. In the moving object predictor, we propose the multi-source fusion structure. First, the spatial importance of each source is highlighted with the help of the interoceptive spatial attention module (ISAM). Second, the motion-enhanced module (MEM) is designed to generate pure foreground motion attention for improving the representation of static and moving features in the decoder. Furthermore, we design a feature purification module (FPM) to filter the inter-source incompatible features. By using the ISAM, MEM and FPM, the multi-source features are effectively fused. In addition, we put forward an adaptive predictor fusion network (APF) to evaluate the quality of the optical flow map and fuse the predictions from the static object predictor and the moving object predictor in order to prevent over-reliance on the failed results caused by low-quality optical flow maps. Experiments show that the proposed model outperforms the state-of-the-art methods on three challenging ZVOS benchmarks. And, the static object predictor precisely predicts a high-quality depth map and static saliency map at the same time.

PaperPDFCode

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

Code

xiaoqi-zhao-dlut/multi-source-aps-zvos officialmentioned in paperpytorch 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

ObjectOptical Flow EstimationSemantic SegmentationUnsupervised Video Object SegmentationVideo Object SegmentationVideo Semantic Segmentation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Video Object Segmentation DAVIS 2016 val AMP F 87.5 #5 of 25 Archive leaderboard report
Unsupervised Video Object Segmentation DAVIS 2016 val AMP G 87.3 #5 of 25 Archive leaderboard report
Unsupervised Video Object Segmentation DAVIS 2016 val AMP J 87.1 #5 of 25 Archive leaderboard report
Unsupervised Video Object Segmentation YouTube-Objects AMP J 75.0 #2 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.

Methods

Average PoolingConvolutionMax PoolingSigmoid Activation

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