Papers › Efficient Regional Memory Network for Video Object Segmentation

Efficient Regional Memory Network for Video Object Segmentation

24 Mar 2021CVPR 2021 1arXiv:2103.12934archive 2025-07-28

Haozhe Xie, Hongxun Yao, Shangchen Zhou, Shengping Zhang, Wenxiu Sun

Recently, several Space-Time Memory based networks have shown that the object cues (e.g. video frames as well as the segmented object masks) from the past frames are useful for segmenting objects in the current frame. However, these methods exploit the information from the memory by global-to-global matching between the current and past frames, which lead to mismatching to similar objects and high computational complexity. To address these problems, we propose a novel local-to-local matching solution for semi-supervised VOS, namely Regional Memory Network (RMNet). In RMNet, the precise regional memory is constructed by memorizing local regions where the target objects appear in the past frames. For the current query frame, the query regions are tracked and predicted based on the optical flow estimated from the previous frame. The proposed local-to-local matching effectively alleviates the ambiguity of similar objects in both memory and query frames, which allows the information to be passed from the regional memory to the query region efficiently and effectively. Experimental results indicate that the proposed RMNet performs favorably against state-of-the-art methods on the DAVIS and YouTube-VOS datasets.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also 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

Syntology 10 code samples harvested from 1 repository linked to this paper: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 10 samples from 1 repository, 5 ran (5 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

hzxie/RMNet officialmentioned on GitHubpytorchSyntology: 10 samples, 5 ran (0 instrument-failed) · 5 unverified 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

10 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

5ran
5unverified

Licence: 0 of the 10 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 hzxie/RMNet. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

hzxie/RMNet official repository 10 samples, 5 ran (0 instrument-failed) · 5 unverified
Decoder in 210 papers models/rmnet.py ran · metamorphic tier: invariant MIT (permissive) · 2825de5a65f2df6f · report fixture: signature r4:Tensor/4/float, r3:Tensor/4/float, r2:Tensor/4/float · returned Tensor · level recorded 2026-09-22
KeyValue models/rmnet.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 49a9e22dab36ada0 · report fixture: signature x:Tensor/4/float · returned tuple · level recorded 2026-09-22
MemoryReader models/rmnet.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 3e5c7b748d94955b · report fixture: signature m_key:Tensor/5/float, m_val:Tensor/5/float, q_key:Tensor/4/float, q_val:Tensor/4/float · returned tuple · level recorded 2026-09-22
Refine in 10 papers models/rmnet.py ran · metamorphic tier: invariant MIT (permissive) · 47c819e0ff62ea4b · report fixture: signature f:Tensor/4/float, pm:Tensor/4/float · returned Tensor · level recorded 2026-09-22
ResBlock in 127 papers
census: 6 implementations from 5 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
models/rmnet.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 80d697d9ca997bc6 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
EncoderMemory models/rmnet.py unverified MIT (permissive) · a64ada2dd41f87cf · report
EncoderQuery models/rmnet.py unverified MIT (permissive) · f3c30027b1d3eb8a · report
RMNet models/rmnet.py unverified MIT (permissive) · a77041027801ccb7 · report
RegionalAttentionMapGenerator models/rmnet.py unverified MIT (permissive) · 3f210dd69e2c0c9c · report
RegionalAttentionMapGeneratorFunction models/rmnet.py unverified MIT (permissive) · cd28fc6fe9cf1306 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Regional Memory Network (RMNet) (graph method: Regional Memory Network (RMNet)). 10 bricks; individually on a fixture: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. RMNet entry · level 0 · unverified · a77041027801ccb7
  2. Decoder model · level 1 · ran · 2825de5a65f2df6f
  3. EncoderMemory model · level 0 · unverified · a64ada2dd41f87cf
  4. EncoderQuery model · level 0 · unverified · f3c30027b1d3eb8a
  5. KeyValue model · level 1 · ran · 49a9e22dab36ada0
  6. MemoryReader model · level 1 · ran · 3e5c7b748d94955b
  7. RegionalAttentionMapGenerator helper · level 0 · unverified · 3f210dd69e2c0c9c
  8. Refine model · level 1 · ran · 47c819e0ff62ea4b
  9. ResBlock helper · level 1 · ran · 80d697d9ca997bc6
  10. RegionalAttentionMapGeneratorFunction helper · level 0 · unverified · cd28fc6fe9cf1306

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2103.12934") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

ObjectOne-shot visual object segmentationOptical Flow EstimationSemantic 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) RMNet D16 val (F) 82.3 #9 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) RMNet D16 val (G) 81.5 #9 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) RMNet D16 val (J) 80.6 #9 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) RMNet D17 val (F) 77.2 #9 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) RMNet D17 val (G) 75.0 #9 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) RMNet D17 val (J) 72.8 #9 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) RMNet FPS 11.9 #9 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 RMNet F-measure (Mean) 88.7 #39 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 RMNet J&F 88.8 #39 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 RMNet Jaccard (Mean) 88.9 #39 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) RMNet F-measure (Mean) 78.1 #34 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) RMNet J&F 75.0 #34 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) RMNet Jaccard (Mean) 71.9 #34 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) RMNet F-measure (Mean) 86.0 #34 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) RMNet J&F 83.5 #34 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) RMNet Jaccard (Mean) 81.0 #34 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 RMNet F-Measure (Seen) 85.7 #36 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 RMNet F-Measure (Unseen) 82.4 #36 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 RMNet Jaccard (Seen) 82.1 #36 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 RMNet Jaccard (Unseen) 75.7 #36 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 RMNet Overall 81.5 #36 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

VOS

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