Papers › Bifurcated backbone strategy for RGB-D salient object detection

Bifurcated backbone strategy for RGB-D salient object detection

6 Jul 2020arXiv:2007.02713archive 2025-07-28

Yingjie Zhai, Deng-Ping Fan, Jufeng Yang, Ali Borji, Ling Shao, Junwei Han, Liang Wang

Multi-level feature fusion is a fundamental topic in computer vision. It has been exploited to detect, segment and classify objects at various scales. When multi-level features meet multi-modal cues, the optimal feature aggregation and multi-modal learning strategy become a hot potato. In this paper, we leverage the inherent multi-modal and multi-level nature of RGB-D salient object detection to devise a novel cascaded refinement network. In particular, first, we propose to regroup the multi-level features into teacher and student features using a bifurcated backbone strategy (BBS). Second, we introduce a depth-enhanced module (DEM) to excavate informative depth cues from the channel and spatial views. Then, RGB and depth modalities are fused in a complementary way. Our architecture, named Bifurcated Backbone Strategy Network (BBS-Net), is simple, efficient, and backbone-independent. Extensive experiments show that BBS-Net significantly outperforms eighteen SOTA models on eight challenging datasets under five evaluation measures, demonstrating the superiority of our approach (∼4 % improvement in S-measure vs. the top-ranked model: DMRA-iccv2019). In addition, we provide a comprehensive analysis on the generalization ability of different RGB-D datasets and provide a powerful training set for future research.

PaperPDFCodeCode 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 5 code samples harvested from 2 repositories linked to this paper: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 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: 4 samples from 1 repository, 3 ran (2 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 1 sample from 1 repository, 1 ran (1 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 4 samples that ran has no recorded date.

zyjwuyan/BBS-Net officialmentioned in papermentioned on GitHubpytorchMITSyntology: 4 samples, 3 ran (1 instrument-failed) · 1 unverified report
DengPingFan/BBS-Net mentioned on GitHubpytorchMITSyntology: 1 sample, 1 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

5 samples harvested: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 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
3ran
1unverified

Licence: 2 of the 5 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, 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.

zyjwuyan/BBS-Net official repository 4 samples, 3 ran (1 instrument-failed) · 1 unverified
conv3x3 in 1,376 papers models/BBSNet_model.py ran · our draft was wrong MIT (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
cv_random_flip in 14 papers data.py ran MIT (permissive) · c5900dcd35b2d0a3 · report fixture: signature img:Image/0/?, label:Image/0/?, depth:Image/0/? · returned tuple · level recorded 2026-09-24
randomCrop in 16 papers data.py ran MIT (permissive) · 7edae4532113d306 · report fixture: signature image:MockImage/0/?, label:MockImage/0/?, depth:MockImage/0/? · returned tuple · level recorded 2026-09-24
randomRotation in 14 papers data.py unverified MIT (permissive) · 2ce2ebcbdb96d573 · report
DengPingFan/BBS-Net community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
adjust_lr in 16 papers utils.py ran MIT (permissive) here; the stored copy is pointer only · 1a4b7ff9d3c48bd7 · report fixture: signature optimizer:SGD/0/?, init_lr:float/0/float, epoch:int/0/int, decay_rate:float/0/float, decay_epoch:int/0/int · returned float · level recorded 2026-09-25

Tasks

ObjectObject DetectionRGB Salient Object DetectionRGB-D Salient Object DetectionSalient Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
RGB-D Salient Object Detection DES BBS-Net Average MAE 0.021 #9 of 13 Archive leaderboard report
RGB-D Salient Object Detection DES BBS-Net S-Measure 93.3 #9 of 13 Archive leaderboard report
RGB-D Salient Object Detection DES BBS-Net max E-Measure 96.6 #9 of 13 Archive leaderboard report
RGB-D Salient Object Detection DES BBS-Net max F-Measure 92.7 #9 of 13 Archive leaderboard report
RGB-D Salient Object Detection LFSD BBS-Net Average MAE 0.072 #5 of 8 Archive leaderboard report
RGB-D Salient Object Detection LFSD BBS-Net S-Measure 86.4 #5 of 8 Archive leaderboard report
RGB-D Salient Object Detection LFSD BBS-Net max E-Measure 90.1 #5 of 8 Archive leaderboard report
RGB-D Salient Object Detection LFSD BBS-Net max F-Measure 85.8 #5 of 8 Archive leaderboard report
RGB-D Salient Object Detection NLPR BBS-Net Average MAE 0.023 #3 of 14 Archive leaderboard report
RGB-D Salient Object Detection NLPR BBS-Net S-Measure 93.0 #3 of 14 Archive leaderboard report
RGB-D Salient Object Detection NLPR BBS-Net max E-Measure 96.1 #3 of 14 Archive leaderboard report
RGB-D Salient Object Detection NLPR BBS-Net max F-Measure 91.8 #3 of 14 Archive leaderboard report
RGB-D Salient Object Detection RGBD135 BBS-Net Average MAE 0.044 #2 of 5 Archive leaderboard report
RGB-D Salient Object Detection RGBD135 BBS-Net S-Measure 88.2 #2 of 5 Archive leaderboard report
RGB-D Salient Object Detection RGBD135 BBS-Net max E-Measure 91.9 #2 of 5 Archive leaderboard report
RGB-D Salient Object Detection RGBD135 BBS-Net max F-Measure 85.9 #2 of 5 Archive leaderboard report
RGB-D Salient Object Detection SIP BBS-Net Average MAE 0.055 #10 of 16 Archive leaderboard report
RGB-D Salient Object Detection SIP BBS-Net S-Measure 87.9 #10 of 16 Archive leaderboard report
RGB-D Salient Object Detection SIP BBS-Net max E-Measure 92.2 #10 of 16 Archive leaderboard report
RGB-D Salient Object Detection SIP BBS-Net max F-Measure 88.3 #10 of 16 Archive leaderboard report
RGB-D Salient Object Detection STERE BBS-Net Average MAE 0.041 #6 of 14 Archive leaderboard report
RGB-D Salient Object Detection STERE BBS-Net S-Measure 90.8 #6 of 14 Archive leaderboard report
RGB-D Salient Object Detection STERE BBS-Net max E-Measure 94.2 #6 of 14 Archive leaderboard report
RGB-D Salient Object Detection STERE BBS-Net max F-Measure 90.3 #6 of 14 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