Papers › Kernelized Memory Network for Video Object Segmentation

Kernelized Memory Network for Video Object Segmentation

16 Jul 2020ECCV 2020 8arXiv:2007.08270archive 2025-07-28

Hongje Seong, Junhyuk Hyun, Euntai Kim

Semi-supervised video object segmentation (VOS) is a task that involves predicting a target object in a video when the ground truth segmentation mask of the target object is given in the first frame. Recently, space-time memory networks (STM) have received significant attention as a promising solution for semi-supervised VOS. However, an important point is overlooked when applying STM to VOS. The solution (STM) is non-local, but the problem (VOS) is predominantly local. To solve the mismatch between STM and VOS, we propose a kernelized memory network (KMN). Before being trained on real videos, our KMN is pre-trained on static images, as in previous works. Unlike in previous works, we use the Hide-and-Seek strategy in pre-training to obtain the best possible results in handling occlusions and segment boundary extraction. The proposed KMN surpasses the state-of-the-art on standard benchmarks by a significant margin (+5% on DAVIS 2017 test-dev set). In addition, the runtime of KMN is 0.12 seconds per frame on the DAVIS 2016 validation set, and the KMN rarely requires extra computation, when compared with STM.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

hkchengrex/Mask-Propagation mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Video Object Segmentation using Space-Time Memory Networks (arXiv:1904.00607; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified) and Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and... (arXiv:2103.07941; that paper's own run record: 10 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 8 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

ObjectSemantic SegmentationSemi-Supervised Video Object SegmentationVideo Object SegmentationVideo Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) KMN D16 val (F) 88.1 #7 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) KMN D16 val (G) 87.6 #7 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) KMN D16 val (J) 87.1 #7 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) KMN D17 val (F) 77.8 #7 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) KMN D17 val (G) 76.0 #7 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) KMN D17 val (J) 74.2 #7 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) KMN FPS 8.33 #7 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 KMN F-measure (Mean) 91.5 #28 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 KMN J&F 90.5 #28 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 KMN Jaccard (Mean) 89.5 #28 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) KMN F-measure (Mean) 80.3 #29 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) KMN J&F 77.2 #29 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) KMN Jaccard (Mean) 74.1 #29 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) KMN F-measure (Mean) 85.6 #36 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) KMN J&F 82.8 #36 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) KMN Jaccard (Mean) 80 #36 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 KMN F-Measure (Seen) 85.6 #37 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 KMN F-Measure (Unseen) 83.3 #37 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 KMN Jaccard (Seen) 81.4 #37 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 KMN Jaccard (Unseen) 75.3 #37 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 KMN Overall 81.4 #37 of 53 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

Memory 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