Papers › Bilateral Reference for High-Resolution Dichotomous Image Segmentation

Bilateral Reference for High-Resolution Dichotomous Image Segmentation

7 Jan 2024arXiv:2401.03407archive 2025-07-28

Peng Zheng, Dehong Gao, Deng-Ping Fan, Li Liu, Jorma Laaksonen, Wanli Ouyang, Nicu Sebe

We introduce a novel bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS). It comprises two essential components: the localization module (LM) and the reconstruction module (RM) with our proposed bilateral reference (BiRef). The LM aids in object localization using global semantic information. Within the RM, we utilize BiRef for the reconstruction process, where hierarchical patches of images provide the source reference and gradient maps serve as the target reference. These components collaborate to generate the final predicted maps. We also introduce auxiliary gradient supervision to enhance focus on regions with finer details. Furthermore, we outline practical training strategies tailored for DIS to improve map quality and training process. To validate the general applicability of our approach, we conduct extensive experiments on four tasks to evince that BiRefNet exhibits remarkable performance, outperforming task-specific cutting-edge methods across all benchmarks. Our codes are available at https://github.com/ZhengPeng7/BiRefNet.

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 14 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 13 ran (10 with no instrument failure; 3 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 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 13 samples that ran has no recorded date.

zhengpeng7/birefnet officialmentioned in papermentioned on GitHubpytorchMITSyntology: 14 samples, 13 ran (3 instrument-failed) · 1 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

14 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 0 violated, 7 with no contract checked; 3 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
2ran · our draft was wrong
1ran; the contract check could not run
7ran
1unverified

Licence: 0 of the 14 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 zhengpeng7/birefnet. “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.

zhengpeng7/birefnet official repository 14 samples, 13 ran (3 instrument-failed) · 1 unverified
FB_blur_fusion_foreground_estimator_cpu_2 image_proc.py ran MIT (permissive) · e7965221ba2e5453 · report fixture: signature image:ndarray/3/float, alpha:ndarray/2/float, r:int/0/int · returned ndarray · level recorded 2026-09-24
SSIM in 17 papers loss.py ran fingerprinted MIT (permissive) · 32a9ebc9a8eebc49 · report fixture: signature x:Tensor/4/float, y:Tensor/4/float · returned Tensor · level recorded 2026-09-24
check_state_dict utils.py ran · our draft was wrong MIT (permissive) · a0f2af79dd5536ac · report fixture: signature state_dict:dict/0/?, unwanted_prefixes:list/1/str · returned dict · level recorded 2026-09-24
create_window in 82 papers loss.py ran · honoured contract fingerprinted MIT (permissive) · 6154e3744ece5728 · report fixture: signature window_size:int/0/int, channel:int/0/int · returned Tensor · level recorded 2026-09-22
gaussian in 218 papers
census: 8 implementations from 9 papers, 8 distinct outputs across 4 buckets, one shared input per bucket
loss.py ran · honoured contract fingerprinted MIT (permissive) · c56b7ef16f309a45 · report fixture: signature window_size:int/0/int, sigma:float/0/float · returned Tensor · level recorded, date not recorded
generate_smoothed_gt utils.py ran · honoured contract fingerprinted MIT (permissive) · 625f65061a0463a9 · report fixture: signature gts:Tensor/2/float · returned Tensor · level recorded 2026-09-24
image2patches models/birefnet.py ran MIT (permissive) · 939c02df4fca5af1 · report fixture: signature image:Tensor/4/float, grid_h:int/0/int, grid_w:int/0/int, patch_ref:Tensor/4/float, transformation:str/0/str · returned Tensor · level recorded 2026-09-24
load_images_parallel evaluation/metrics.py ran MIT (permissive) · a769e9d2c7633ce9 · report fixture: signature gt_paths:list/1/str, pred_paths:list/1/str, num_workers:int/0/int, verbose:bool/0/bool · returned list · level recorded 2026-09-24
load_single_image_pair evaluation/metrics.py ran · our draft was wrong fingerprinted MIT (permissive) · fb4f4bbd0eb2e5b6 · report fixture: signature args:tuple/1/str · returned dict · level recorded 2026-09-24
mean_blur image_proc.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 76639f9e42708b4e · report fixture: signature x:Tensor/4/float, kernel_size:int/0/int · returned Tensor · level recorded 2026-09-24
patches2image models/birefnet.py ran MIT (permissive) · 05e78beaf2a1a37a · report fixture: signature patches:Tensor/4/float, grid_h:int/0/int, grid_w:int/0/int, patch_ref:NoneType/0/?, transformation:str/0/str · returned Tensor · level recorded 2026-09-24
path_to_image utils.py ran MIT (permissive) · f66e6359cff25940 · report fixture: signature path:str/0/str, size:tuple/1/int, color_type:str/0/str · returned Image · level recorded 2026-09-24
process_metrics_single evaluation/metrics.py ran MIT (permissive) · dcd0a21071a6862c · report fixture: signature data:dict/0/?, measures:dict/0/?, metrics:list/1/str · returned dict · level recorded 2026-09-24
FB_blur_fusion_foreground_estimator_cpu image_proc.py unverified MIT (permissive) · 0799073430991c59 · report

Tasks

Camouflaged Object SegmentationDichotomous Image SegmentationImage SegmentationObject LocalizationRGB Salient Object DetectionSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Camouflaged Object Segmentation CAMO BiRefNet MAE 0.030 #2 of 14 Archive leaderboard report
Camouflaged Object Segmentation CAMO BiRefNet S-Measure 0.904 #2 of 14 Archive leaderboard report
Camouflaged Object Segmentation CAMO BiRefNet Weighted F-Measure 0.890 #2 of 14 Archive leaderboard report
Camouflaged Object Segmentation CHAMELEON BiRefNet MAE 0.015 #1 of 6 Archive leaderboard report
Camouflaged Object Segmentation CHAMELEON BiRefNet S-measure 0.932 #1 of 6 Archive leaderboard report
Camouflaged Object Segmentation CHAMELEON BiRefNet weighted F-measure 0.914 #1 of 6 Archive leaderboard report
Camouflaged Object Segmentation COD BiRefNet MAE 0.014 #1 of 12 Archive leaderboard report
Camouflaged Object Segmentation COD BiRefNet S-Measure 0.913 #1 of 12 Archive leaderboard report
Camouflaged Object Segmentation COD BiRefNet Weighted F-Measure 0.874 #1 of 12 Archive leaderboard report
Camouflaged Object Segmentation NC4K BiRefNet MAE 0.023 #2 of 6 Archive leaderboard report
Camouflaged Object Segmentation NC4K BiRefNet S-measure 0.914 #2 of 6 Archive leaderboard report
Camouflaged Object Segmentation NC4K BiRefNet weighted F-measure 0.894 #2 of 6 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 BiRefNet E-measure 0.908 #3 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 BiRefNet HCE 106 #3 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 BiRefNet MAE 0.038 #3 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 BiRefNet S-Measure 0.882 #3 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 BiRefNet max F-Measure 0.855 #3 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE1 BiRefNet weighted F-measure 0.814 #3 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 BiRefNet E-measure 0.935 #3 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 BiRefNet HCE 265 #3 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 BiRefNet MAE 0.035 #3 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 BiRefNet S-Measure 0.904 #3 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 BiRefNet max F-Measure 0.898 #3 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE2 BiRefNet weighted F-measure 0.863 #3 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 BiRefNet E-measure 0.952 #3 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 BiRefNet HCE 573 #3 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 BiRefNet MAE 0.030 #3 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 BiRefNet S-Measure 0.918 #3 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 BiRefNet max F-Measure 0.923 #3 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE3 BiRefNet weighted F-measure 0.891 #3 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 BiRefNet E-measure 0.937 #4 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 BiRefNet HCE 2746 #4 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 BiRefNet MAE 0.040 #4 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 BiRefNet S-Measure 0.898 #4 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 BiRefNet max F-Measure 0.900 #4 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-TE4 BiRefNet weighted F-measure 0.861 #4 of 22 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD BiRefNet E-measure 0.928 #5 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD BiRefNet HCE 1006 #5 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD BiRefNet MAE 0.038 #5 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD BiRefNet S-Measure 0.898 #5 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD BiRefNet max F-Measure 0.889 #5 of 24 Archive leaderboard report
Dichotomous Image Segmentation DIS-VD BiRefNet weighted F-measure 0.853 #5 of 24 Archive leaderboard report
RGB Salient Object Detection DAVIS-S BiRefNet (HRSOD, UHRSD) F-measure 0.980 #1 of 12 Archive leaderboard report
RGB Salient Object Detection DAVIS-S BiRefNet (HRSOD, UHRSD) MAE 0.006 #1 of 12 Archive leaderboard report
RGB Salient Object Detection DAVIS-S BiRefNet (HRSOD, UHRSD) S-measure 0.976 #1 of 12 Archive leaderboard report
RGB Salient Object Detection DAVIS-S BiRefNet (DUTS, HRSOD, UHRSD) F-measure 0.979 #2 of 12 Archive leaderboard report
RGB Salient Object Detection DAVIS-S BiRefNet (DUTS, HRSOD, UHRSD) MAE 0.006 #2 of 12 Archive leaderboard report
RGB Salient Object Detection DAVIS-S BiRefNet (DUTS, HRSOD, UHRSD) S-measure 0.975 #2 of 12 Archive leaderboard report
RGB Salient Object Detection DAVIS-S BiRefNet (DUTS, UHRSD) F-measure 0.977 #3 of 12 Archive leaderboard report
RGB Salient Object Detection DAVIS-S BiRefNet (DUTS, UHRSD) MAE 0.006 #3 of 12 Archive leaderboard report
RGB Salient Object Detection DAVIS-S BiRefNet (DUTS, UHRSD) S-measure 0.975 #3 of 12 Archive leaderboard report
RGB Salient Object Detection DAVIS-S BiRefNet (DUTS, HRSOD) F-measure 0.976 #4 of 12 Archive leaderboard report
RGB Salient Object Detection DAVIS-S BiRefNet (DUTS, HRSOD) MAE 0.006 #4 of 12 Archive leaderboard report
RGB Salient Object Detection DAVIS-S BiRefNet (DUTS, HRSOD) S-measure 0.973 #4 of 12 Archive leaderboard report
RGB Salient Object Detection DAVIS-S BiRefNet (DUTS) F-measure 0.966 #6 of 12 Archive leaderboard report
RGB Salient Object Detection DAVIS-S BiRefNet (DUTS) MAE 0.008 #6 of 12 Archive leaderboard report
RGB Salient Object Detection DAVIS-S BiRefNet (DUTS) S-measure 0.967 #6 of 12 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (DUTS, HRSOD, UHRSD) F-measure 0.839 #1 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (DUTS, HRSOD, UHRSD) MAE 0.038 #1 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (DUTS, HRSOD, UHRSD) S-Measure 0.882 #1 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (DUTS, HRSOD, UHRSD) Weighted F-Measure 0.815 #1 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (DUTS, HRSOD, UHRSD) mean E-Measure 0.896 #1 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (DUTS, HRSOD, UHRSD) mean F-Measure 0.825 #1 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (DUTS, UHRSD) F-measure 0.837 #2 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (DUTS, UHRSD) MAE 0.036 #2 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (DUTS, UHRSD) S-Measure 0.881 #2 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (DUTS, UHRSD) Weighted F-Measure 0.815 #2 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (DUTS, UHRSD) mean E-Measure 0.896 #2 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (DUTS, UHRSD) mean F-Measure 0.825 #2 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (DUTS, HRSOD) F-measure 0.818 #5 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (DUTS, HRSOD) MAE 0.040 #5 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (DUTS, HRSOD) S-Measure 0.868 #5 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (DUTS, HRSOD) Weighted F-Measure 0.800 #5 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (DUTS, HRSOD) mean E-Measure 0.882 #5 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (DUTS, HRSOD) mean F-Measure 0.809 #5 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (DUTS) F-measure 0.813 #6 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (DUTS) MAE 0.040 #6 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (DUTS) S-Measure 0.868 #6 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (DUTS) Weighted F-Measure 0.792 #6 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (DUTS) mean E-Measure 0.878 #6 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (DUTS) mean F-Measure 0.802 #6 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (HRSOD, UHRSD) F-measure 0.810 #7 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (HRSOD, UHRSD) MAE 0.040 #7 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (HRSOD, UHRSD) S-Measure 0.864 #7 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (HRSOD, UHRSD) Weighted F-Measure 0.790 #7 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (HRSOD, UHRSD) mean E-Measure 0.879 #7 of 18 Archive leaderboard report
RGB Salient Object Detection DUT-OMRON BiRefNet (HRSOD, UHRSD) mean F-Measure 0.801 #7 of 18 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (DUTS, HRSOD, UHRSD) MAE 0.018 #1 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (DUTS, HRSOD, UHRSD) S-Measure 0.944 #1 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (DUTS, HRSOD, UHRSD) Weighted F-Measure 0.920 #1 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (DUTS, HRSOD, UHRSD) max F-measure 0.943 #1 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (DUTS, HRSOD, UHRSD) mean E-Measure 0.962 #1 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (DUTS, HRSOD, UHRSD) mean F-Measure 0.925 #1 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (DUTS, UHRSD) MAE 0.018 #2 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (DUTS, UHRSD) S-Measure 0.942 #2 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (DUTS, UHRSD) Weighted F-Measure 0.919 #2 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (DUTS, UHRSD) max F-measure 0.942 #2 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (DUTS, UHRSD) mean E-Measure 0.961 #2 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (DUTS, UHRSD) mean F-Measure 0.925 #2 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (DUTS) MAE 0.019 #3 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (DUTS) S-Measure 0.939 #3 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (DUTS) Weighted F-Measure 0.913 #3 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (DUTS) max F-measure 0.937 #3 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (DUTS) mean E-Measure 0.958 #3 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (DUTS) mean F-Measure 0.919 #3 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (DUTS, HRSOD) MAE 0.018 #4 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (DUTS, HRSOD) S-Measure 0.938 #4 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (DUTS, HRSOD) Weighted F-Measure 0.918 #4 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (DUTS, HRSOD) max F-measure 0.935 #4 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (DUTS, HRSOD) mean E-Measure 0.960 #4 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (DUTS, HRSOD) mean F-Measure 0.923 #4 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (HRSOD, UHRSD) MAE 0.020 #5 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (HRSOD, UHRSD) S-Measure 0.933 #5 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (HRSOD, UHRSD) Weighted F-Measure 0.907 #5 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (HRSOD, UHRSD) max F-measure 0.928 #5 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (HRSOD, UHRSD) mean E-Measure 0.954 #5 of 31 Archive leaderboard report
RGB Salient Object Detection DUTS-TE BiRefNet (HRSOD, UHRSD) mean F-Measure 0.913 #5 of 31 Archive leaderboard report
RGB Salient Object Detection HRSOD BiRefNet (DUTS, HRSOD) MAE 0.011 #2 of 14 Archive leaderboard report
RGB Salient Object Detection HRSOD BiRefNet (DUTS, HRSOD) S-Measure 0.962 #2 of 14 Archive leaderboard report
RGB Salient Object Detection HRSOD BiRefNet (DUTS, HRSOD) max F-Measure 0.963 #2 of 14 Archive leaderboard report
RGB Salient Object Detection HRSOD BiRefNet (DUTS, HRSOD, UHRSD) MAE 0.013 #3 of 14 Archive leaderboard report
RGB Salient Object Detection HRSOD BiRefNet (DUTS, HRSOD, UHRSD) S-Measure 0.962 #3 of 14 Archive leaderboard report
RGB Salient Object Detection HRSOD BiRefNet (DUTS, HRSOD, UHRSD) max F-Measure 0.961 #3 of 14 Archive leaderboard report
RGB Salient Object Detection HRSOD BiRefNet (DUTS, UHRSD) MAE 0.014 #5 of 14 Archive leaderboard report
RGB Salient Object Detection HRSOD BiRefNet (DUTS, UHRSD) S-Measure 0.959 #5 of 14 Archive leaderboard report
RGB Salient Object Detection HRSOD BiRefNet (DUTS, UHRSD) max F-Measure 0.958 #5 of 14 Archive leaderboard report
RGB Salient Object Detection HRSOD BiRefNet (DUTS) MAE 0.014 #6 of 14 Archive leaderboard report
RGB Salient Object Detection HRSOD BiRefNet (DUTS) S-Measure 0.957 #6 of 14 Archive leaderboard report
RGB Salient Object Detection HRSOD BiRefNet (DUTS) max F-Measure 0.958 #6 of 14 Archive leaderboard report
RGB Salient Object Detection HRSOD BiRefNet (HRSOD, UHRSD) MAE 0.016 #8 of 14 Archive leaderboard report
RGB Salient Object Detection HRSOD BiRefNet (HRSOD, UHRSD) S-Measure 0.956 #8 of 14 Archive leaderboard report
RGB Salient Object Detection HRSOD BiRefNet (HRSOD, UHRSD) max F-Measure 0.953 #8 of 14 Archive leaderboard report
RGB Salient Object Detection UHRSD BiRefNet (DUTS, HRSOD, UHRSD) MAE 0.016 #1 of 12 Archive leaderboard report
RGB Salient Object Detection UHRSD BiRefNet (DUTS, HRSOD, UHRSD) S-Measure 0.957 #1 of 12 Archive leaderboard report
RGB Salient Object Detection UHRSD BiRefNet (DUTS, HRSOD, UHRSD) max F-Measure 0.963 #1 of 12 Archive leaderboard report
RGB Salient Object Detection UHRSD BiRefNet (DUTS, UHRSD) MAE 0.019 #4 of 12 Archive leaderboard report
RGB Salient Object Detection UHRSD BiRefNet (DUTS, UHRSD) S-Measure 0.952 #4 of 12 Archive leaderboard report
RGB Salient Object Detection UHRSD BiRefNet (DUTS, UHRSD) max F-Measure 0.960 #4 of 12 Archive leaderboard report
RGB Salient Object Detection UHRSD BiRefNet (HRSOD, UHRSD) MAE 0.019 #5 of 12 Archive leaderboard report
RGB Salient Object Detection UHRSD BiRefNet (HRSOD, UHRSD) S-Measure 0.952 #5 of 12 Archive leaderboard report
RGB Salient Object Detection UHRSD BiRefNet (HRSOD, UHRSD) max F-Measure 0.958 #5 of 12 Archive leaderboard report
RGB Salient Object Detection UHRSD BiRefNet (DUTS, HRSOD) MAE 0.024 #6 of 12 Archive leaderboard report
RGB Salient Object Detection UHRSD BiRefNet (DUTS, HRSOD) S-Measure 0.937 #6 of 12 Archive leaderboard report
RGB Salient Object Detection UHRSD BiRefNet (DUTS, HRSOD) max F-Measure 0.942 #6 of 12 Archive leaderboard report
RGB Salient Object Detection UHRSD BiRefNet (DUTS) MAE 0.030 #10 of 12 Archive leaderboard report
RGB Salient Object Detection UHRSD BiRefNet (DUTS) S-Measure 0.931 #10 of 12 Archive leaderboard report
RGB Salient Object Detection UHRSD BiRefNet (DUTS) max F-Measure 0.933 #10 of 12 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

Focus

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