Papers › See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks

See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks

19 Jan 2020CVPR 2019 6arXiv:2001.06810archive 2025-07-28

Xiankai Lu, Wenguan Wang, Chao Ma, Jianbing Shen, Ling Shao, Fatih Porikli

We introduce a novel network, called CO-attention Siamese Network (COSNet), to address the unsupervised video object segmentation task from a holistic view. We emphasize the importance of inherent correlation among video frames and incorporate a global co-attention mechanism to improve further the state-of-the-art deep learning based solutions that primarily focus on learning discriminative foreground representations over appearance and motion in short-term temporal segments. The co-attention layers in our network provide efficient and competent stages for capturing global correlations and scene context by jointly computing and appending co-attention responses into a joint feature space. We train COSNet with pairs of video frames, which naturally augments training data and allows increased learning capacity. During the segmentation stage, the co-attention model encodes useful information by processing multiple reference frames together, which is leveraged to infer the frequently reappearing and salient foreground objects better. We propose a unified and end-to-end trainable framework where different co-attention variants can be derived for mining the rich context within videos. Our extensive experiments over three large benchmarks manifest that COSNet outperforms the current alternatives by a large margin.

PaperPDFConference PDFCode

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

Code

carrierlxk/COSNet 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

Semantic SegmentationUnsupervised Video Object SegmentationVideo Object SegmentationVideo Polyp SegmentationVideo Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Video Object Segmentation DAVIS 2016 val COSNet F 79.4 #22 of 25 Archive leaderboard report
Unsupervised Video Object Segmentation DAVIS 2016 val COSNet G 80.0 #22 of 25 Archive leaderboard report
Unsupervised Video Object Segmentation DAVIS 2016 val COSNet J 80.5 #22 of 25 Archive leaderboard report
Unsupervised Video Object Segmentation FBMS test COSNet J 75.6 #14 of 15 Archive leaderboard report
Unsupervised Video Object Segmentation YouTube-Objects COSNet J 70.5 #11 of 16 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Easy (Unseen) COSNet Dice 0.596 #13 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Easy (Unseen) COSNet S measure 0.654 #13 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Easy (Unseen) COSNet Sensitivity 0.359 #13 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Easy (Unseen) COSNet mean E-measure 0.600 #13 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Easy (Unseen) COSNet mean F-measure 0.496 #13 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Easy (Unseen) COSNet weighted F-measure 0.431 #13 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Hard (Unseen) COSNet Dice 0.606 #11 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Hard (Unseen) COSNet S-Measure 0.670 #11 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Hard (Unseen) COSNet Sensitivity 0.380 #11 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Hard (Unseen) COSNet mean E-measure 0.627 #11 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Hard (Unseen) COSNet mean F-measure 0.506 #11 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Hard (Unseen) COSNet weighted F-measure 0.443 #11 of 18 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

Siamese Network

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