Papers › Full-Duplex Strategy for Video Object Segmentation

Full-Duplex Strategy for Video Object Segmentation

6 Aug 2021ICCV 2021 10arXiv:2108.03151archive 2025-07-28

Ge-Peng Ji, Deng-Ping Fan, Keren Fu, Zhe Wu, Jianbing Shen, Ling Shao

Previous video object segmentation approaches mainly focus on using simplex solutions between appearance and motion, limiting feature collaboration efficiency among and across these two cues. In this work, we study a novel and efficient full-duplex strategy network (FSNet) to address this issue, by considering a better mutual restraint scheme between motion and appearance in exploiting the cross-modal features from the fusion and decoding stage. Specifically, we introduce the relational cross-attention module (RCAM) to achieve bidirectional message propagation across embedding sub-spaces. To improve the model's robustness and update the inconsistent features from the spatial-temporal embeddings, we adopt the bidirectional purification module (BPM) after the RCAM. Extensive experiments on five popular benchmarks show that our FSNet is robust to various challenging scenarios (e.g., motion blur, occlusion) and achieves favourable performance against existing cutting-edges both in the video object segmentation and video salient object detection tasks. The project is publicly available at: https://dpfan.net/FSNet.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2108.03151")

Code

Syntology Ran 7 of 8 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 7 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

GewelsJI/FSNet officialmentioned on GitHubpytorch 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

8 samples harvested; 7 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

7ran
1unverified

Licence: 0 of the 8 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from GewelsJI/FSNet. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

BPM GewelsJI/FSNet/lib/fsnet.py official repository ran Apache-2.0 (permissive) · 396efed75928c79c · report
BasicConv2d GewelsJI/FSNet/lib/fsnet.py official repository ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 9d65fd2b9de9e302 · report
Decoder GewelsJI/FSNet/lib/fsnet.py official repository ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 7d142ec657be7a17 · report
DimReduce GewelsJI/FSNet/lib/fsnet.py official repository ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · b87d230de5341d9c · report
PyramidPooling GewelsJI/FSNet/lib/fsnet.py official repository ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · dfbf76d4ebcee7c3 · report
ResNet50 GewelsJI/FSNet/lib/fsnet.py official repository ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · a42e339cce788ad4 · report
conv_upsample GewelsJI/FSNet/lib/fsnet.py official repository ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 5d8bdcbcbac6daf1 · report
FSNet GewelsJI/FSNet/lib/fsnet.py official repository unverified Apache-2.0 (permissive) · 710857c7b9a46774 · report

Tasks

ObjectObject DetectionSalient Object DetectionSegmentationSemantic SegmentationUnsupervised Video Object SegmentationVideo Object SegmentationVideo Polyp SegmentationVideo Salient Object DetectionVideo Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Video Object Segmentation DAVIS 2016 val FSNet F 83.1 #17 of 25 Archive leaderboard report
Unsupervised Video Object Segmentation DAVIS 2016 val FSNet G 83.3 #17 of 25 Archive leaderboard report
Unsupervised Video Object Segmentation DAVIS 2016 val FSNet J 83.4 #17 of 25 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Easy (Unseen) FSNet Dice 0.702 #9 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Easy (Unseen) FSNet S measure 0.725 #9 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Easy (Unseen) FSNet Sensitivity 0.493 #9 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Easy (Unseen) FSNet mean E-measure 0.695 #9 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Easy (Unseen) FSNet mean F-measure 0.630 #9 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Easy (Unseen) FSNet weighted F-measure 0.551 #9 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Hard (Unseen) FSNet Dice 0.699 #9 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Hard (Unseen) FSNet S-Measure 0.724 #9 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Hard (Unseen) FSNet Sensitivity 0.491 #9 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Hard (Unseen) FSNet mean E-measure 0.694 #9 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Hard (Unseen) FSNet mean F-measure 0.611 #9 of 18 Archive leaderboard report
Video Polyp Segmentation SUN-SEG-Hard (Unseen) FSNet weighted F-measure 0.541 #9 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

Concatenated Skip ConnectionSoftmaxVOS

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