Papers › Online Adaptation of Convolutional Neural Networks for Video Object Segmentation

Online Adaptation of Convolutional Neural Networks for Video Object Segmentation

28 Jun 2017arXiv:1706.09364archive 2025-07-28

Paul Voigtlaender, Bastian Leibe

We tackle the task of semi-supervised video object segmentation, i.e. segmenting the pixels belonging to an object in the video using the ground truth pixel mask for the first frame. We build on the recently introduced one-shot video object segmentation (OSVOS) approach which uses a pretrained network and fine-tunes it on the first frame. While achieving impressive performance, at test time OSVOS uses the fine-tuned network in unchanged form and is not able to adapt to large changes in object appearance. To overcome this limitation, we propose Online Adaptive Video Object Segmentation (OnAVOS) which updates the network online using training examples selected based on the confidence of the network and the spatial configuration. Additionally, we add a pretraining step based on objectness, which is learned on PASCAL. Our experiments show that both extensions are highly effective and improve the state of the art on DAVIS to an intersection-over-union score of 85.7%.

PaperPDF

In Syntology View this paper on Syntology: its page in Syntology's graph, with its repositories and citations.

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ObjectSegmentationSemantic SegmentationSemi-Supervised Video Object SegmentationVideo Object SegmentationVideo Semantic SegmentationVisual Object Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Video Object Segmentation DAVIS 2016 OnAVOS F-measure (Decay) 5.8 #50 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 OnAVOS F-measure (Mean) 84.9 #50 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 OnAVOS F-measure (Recall) 89.7 #50 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 OnAVOS J&F 85.5 #50 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 OnAVOS Jaccard (Decay) 5.2 #50 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 OnAVOS Jaccard (Mean) 86.1 #50 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 OnAVOS Jaccard (Recall) 96.1 #50 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) OnAVOS F-measure (Decay) 23.4 #52 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) OnAVOS F-measure (Recall) 60.3 #52 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) OnAVOS J&F 52.8 #52 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) OnAVOS Jaccard (Decay) 23.0 #52 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) OnAVOS Jaccard (Mean) 49.9 #52 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) OnAVOS Jaccard (Recall) 54.3 #52 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) OnAVOS F-measure (Decay) 26.6 #68 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) OnAVOS F-measure (Mean) 69.1 #68 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) OnAVOS F-measure (Recall) 75.4 #68 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) OnAVOS J&F 65.35 #68 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) OnAVOS Jaccard (Decay) 27.9 #68 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) OnAVOS Jaccard (Mean) 61.6 #68 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) OnAVOS Jaccard (Recall) 67.4 #68 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube OnAVOS mIoU 0.774 #4 of 5 Archive leaderboard report
Visual Object Tracking YouTube-VOS 2018 OnAVOS F-Measure (Seen) 62.7 #2 of 9 Archive leaderboard report
Visual Object Tracking YouTube-VOS 2018 OnAVOS F-Measure (Unseen) 51.4 #2 of 9 Archive leaderboard report
Visual Object Tracking YouTube-VOS 2018 OnAVOS Jaccard (Seen) 60.1 #2 of 9 Archive leaderboard report
Visual Object Tracking YouTube-VOS 2018 OnAVOS Jaccard (Unseen) 46.6 #2 of 9 Archive leaderboard report
Visual Object Tracking YouTube-VOS 2018 OnAVOS O (Average of Measures) 55.2 #2 of 9 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