Papers › RANet: Ranking Attention Network for Fast Video Object Segmentation

RANet: Ranking Attention Network for Fast Video Object Segmentation

19 Aug 2019ICCV 2019 10arXiv:1908.06647archive 2025-07-28

Ziqin Wang, Jun Xu, Li Liu, Fan Zhu, Ling Shao

Despite online learning (OL) techniques have boosted the performance of semi-supervised video object segmentation (VOS) methods, the huge time costs of OL greatly restrict their practicality. Matching based and propagation based methods run at a faster speed by avoiding OL techniques. However, they are limited by sub-optimal accuracy, due to mismatching and drifting problems. In this paper, we develop a real-time yet very accurate Ranking Attention Network (RANet) for VOS. Specifically, to integrate the insights of matching based and propagation based methods, we employ an encoder-decoder framework to learn pixel-level similarity and segmentation in an end-to-end manner. To better utilize the similarity maps, we propose a novel ranking attention module, which automatically ranks and selects these maps for fine-grained VOS performance. Experiments on DAVIS-16 and DAVIS-17 datasets show that our RANet achieves the best speed-accuracy trade-off, e.g., with 33 milliseconds per frame and J&F=85.5% on DAVIS-16. With OL, our RANet reaches J&F=87.1% on DAVIS-16, exceeding state-of-the-art VOS methods. The code can be found at https://github.com/Storife/RANet.

PaperPDFConference PDFCodeCode Syntology ran

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 12 code samples harvested from 2 repositories linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 1 repository, 8 ran (7 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 3 samples from 1 repository, 3 ran (3 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 between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 11 samples that ran has no recorded date.

Storife/RANet officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 9 samples, 8 ran (1 instrument-failed) · 1 unverified report
v1viswan/RANet_modifications mentioned on GitHubpytorchApache-2.0Syntology: 3 samples, 3 ran (0 instrument-failed) · 0 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

12 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 1 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.

1ran · our draft was wrong
10ran
1unverified

Licence: 1 of the 12 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

Storife/RANet official repository 9 samples, 8 ran (1 instrument-failed) · 1 unverified
Data_combinePicNameList codes/RANet_lib/RANet_DATA_loader.py ran Apache-2.0 (permissive) · 17c2725831c1b925 · report fixture: signature data_list:list/1/dict · returned dict · level recorded 2026-09-25
bbox_crop codes/RANet_lib/RANet_lib.py ran Apache-2.0 (permissive) · 2d6d8d058d6ee1cf · report fixture: signature img:Tensor/3/float, bbox:list/1/int · returned Tensor · level recorded 2026-09-25
conv3x3 in 1,376 papers codes/RANet_lib/RANet_resnet_ins.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · fac5364e2f53c6db · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
get_imagenet_model codes/RANet_lib/RANet_Model_imagenet.py ran Apache-2.0 (permissive) · 0d10f19c6657d0e0 · report fixture: signature type:str/0/str, pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-25
get_imagenet_model codes/RANet_lib/Resnet_ins101.py ran Apache-2.0 (permissive) · 1f5fe5bccb134719 · report fixture: signature type:str/0/str, pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-25
make_layer2 codes/RANet_model.py ran Apache-2.0 (permissive) · ba18985adbbee7fd · report fixture: signature input_feature:int/0/int, out_feature:int/0/int, up_scale:int/0/int, ksize:int/0/int, d:int/0/int, groups:int/0/int · returned Sequential · level recorded 2026-09-25
msk2bbox codes/RANet_lib/RANet_lib.py ran Apache-2.0 (permissive) · a3591e754555960f · report fixture: signature msk:Tensor/3/float, k:float/0/float · returned Tensor · level recorded 2026-09-25
resnet_ins101 codes/RANet_lib/RANet_resnet_ins.py ran Apache-2.0 (permissive) · ae58bcdbb1c048c0 · report fixture: signature pretrained:bool/0/bool · returned ResNet_ins · level recorded 2026-09-25
checkpoint_load codes/RANet_lib/RANet_lib.py unverified Apache-2.0 (permissive) · 21179515d0388b55 · report
v1viswan/RANet_modifications community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
make_layer2 codes/RANet_model.py ran Apache-2.0 (permissive) · 25478e593024c8f9 · report fixture: signature input_feature:int/0/int, out_feature:int/0/int, up_scale:int/0/int, ksize:int/0/int, d:int/0/int, groups:int/0/int · returned Sequential · level recorded 2026-09-24
msk2bbox codes/RANet_lib/RANet_lib.py ran Apache-2.0 (permissive) · 2b58e4965c15d608 · report fixture: signature msk:Tensor/3/float, k:float/0/float · returned Tensor · level recorded 2026-09-24
nms_excitation codes/RANet_model.py ran Apache-2.0 (permissive) · ce75ee8116383c03 · report fixture: signature score_map:Tensor/4/float, excitation_score:float/0/float, threshold:float/0/float, window_size:int/0/int · returned Tensor · level recorded 2026-09-24

Tasks

DecoderObjectSemantic 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) RANet D16 val (F) 85.4 #24 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) RANet D16 val (G) 85.5 #24 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) RANet D16 val (J) 85.5 #24 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) RANet D17 test (F) 57.2 #24 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) RANet D17 test (G) 55.3 #24 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) RANet D17 test (J) 53.4 #24 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) RANet D17 val (F) 68.2 #24 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) RANet D17 val (G) 65.7 #24 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) RANet D17 val (J) 63.2 #24 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) RANet FPS 30.3 #24 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 RANet+ (online learning) F-measure (Decay) 8.2 #43 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 RANet+ (online learning) F-measure (Mean) 87.6 #43 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 RANet+ (online learning) F-measure (Recall) 96.1 #43 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 RANet+ (online learning) J&F 87.1 #43 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 RANet+ (online learning) Jaccard (Decay) 7.4 #43 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 RANet+ (online learning) Jaccard (Mean) 86.6 #43 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 RANet+ (online learning) Jaccard (Recall) 97 #43 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 RANet F-measure (Decay) 5.1 #51 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 RANet F-measure (Mean) 85.4 #51 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 RANet F-measure (Recall) 94.9 #51 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 RANet J&F 85.45 #51 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 RANet Jaccard (Decay) 6.2 #51 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 RANet Jaccard (Mean) 85.5 #51 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 RANet Jaccard (Recall) 97.2 #51 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) RANet F-measure (Decay) 22.1 #49 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) RANet F-measure (Mean) 57.3 #49 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) RANet F-measure (Recall) 67.7 #49 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) RANet J&F 55.4 #49 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) RANet Jaccard (Decay) 21.9 #49 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) RANet Jaccard (Mean) 53.4 #49 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) RANet Jaccard (Recall) 61.9 #49 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) RANet F-measure (Decay) 19.7 #66 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) RANet F-measure (Mean) 68.2 #66 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) RANet F-measure (Recall) 78.8 #66 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) RANet J&F 65.7 #66 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) RANet Jaccard (Decay) 18.6 #66 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) RANet Jaccard (Mean) 63.2 #66 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) RANet Jaccard (Recall) 73.7 #66 of 81 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

SPEED

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