</> Code with Papers by Syntology

Papers › Bilateral Attention Network for RGB-D Salient Object Detection

Bilateral Attention Network for RGB-D Salient Object Detection

30 Apr 2020arXiv:2004.14582archive 2025-07-28

Zhao Zhang, Zheng Lin, Jun Xu, Wenda Jin, Shao-Ping Lu, Deng-Ping Fan

Most existing RGB-D salient object detection (SOD) methods focus on the foreground region when utilizing the depth images. However, the background also provides important information in traditional SOD methods for promising performance. To better explore salient information in both foreground and background regions, this paper proposes a Bilateral Attention Network (BiANet) for the RGB-D SOD task. Specifically, we introduce a Bilateral Attention Module (BAM) with a complementary attention mechanism: foreground-first (FF) attention and background-first (BF) attention. The FF attention focuses on the foreground region with a gradual refinement style, while the BF one recovers potentially useful salient information in the background region. Benefitted from the proposed BAM module, our BiANet can capture more meaningful foreground and background cues, and shift more attention to refining the uncertain details between foreground and background regions. Additionally, we extend our BAM by leveraging the multi-scale techniques for better SOD performance. Extensive experiments on six benchmark datasets demonstrate that our BiANet outperforms other state-of-the-art RGB-D SOD methods in terms of objective metrics and subjective visual comparison. Our BiANet can run up to 80fps on 224×224 RGB-D images, with an NVIDIA GeForce RTX 2080Ti GPU. Comprehensive ablation studies also validate our contributions.

PaperPDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

Code

zzhanghub/bianet mentioned 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

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

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
RGB-D Salient Object Detection DES BiANet Average MAE 0.021 #10 of 13 Archive leaderboard report
RGB-D Salient Object Detection DES BiANet S-Measure 93.1 #10 of 13 Archive leaderboard report
RGB-D Salient Object Detection DES BiANet max E-Measure 97.1 #10 of 13 Archive leaderboard report
RGB-D Salient Object Detection DES BiANet max F-Measure 92.6 #10 of 13 Archive leaderboard report
RGB-D Salient Object Detection LFSD BiANet Average MAE 0.0x #8 of 8 Archive leaderboard report
RGB-D Salient Object Detection NJU2K BiANet Average MAE 0.039 #5 of 27 Archive leaderboard report
RGB-D Salient Object Detection NJU2K BiANet S-Measure 91.5 #5 of 27 Archive leaderboard report
RGB-D Salient Object Detection NJU2K BiANet max E-Measure 94.8 #5 of 27 Archive leaderboard report
RGB-D Salient Object Detection NJU2K BiANet max F-Measure 92.0 #5 of 27 Archive leaderboard report
RGB-D Salient Object Detection NLPR BiANet Average MAE 0.024 #8 of 14 Archive leaderboard report
RGB-D Salient Object Detection NLPR BiANet S-Measure 92.5 #8 of 14 Archive leaderboard report
RGB-D Salient Object Detection NLPR BiANet max E-Measure 96.1 #8 of 14 Archive leaderboard report
RGB-D Salient Object Detection NLPR BiANet max F-Measure 91.4 #8 of 14 Archive leaderboard report
RGB-D Salient Object Detection RGBD135 BiANet Average MAE 0.050 #3 of 5 Archive leaderboard report
RGB-D Salient Object Detection RGBD135 BiANet S-Measure 86.7 #3 of 5 Archive leaderboard report
RGB-D Salient Object Detection RGBD135 BiANet max E-Measure 91.6 #3 of 5 Archive leaderboard report
RGB-D Salient Object Detection RGBD135 BiANet max F-Measure 84.9 #3 of 5 Archive leaderboard report
RGB-D Salient Object Detection SIP BiANet Average MAE 0.052 #8 of 16 Archive leaderboard report
RGB-D Salient Object Detection SIP BiANet S-Measure 88.3 #8 of 16 Archive leaderboard report
RGB-D Salient Object Detection SIP BiANet max E-Measure 92.5 #8 of 16 Archive leaderboard report
RGB-D Salient Object Detection SIP BiANet max F-Measure 89.0 #8 of 16 Archive leaderboard report
RGB-D Salient Object Detection STERE BiANet Average MAE 0.043 #10 of 14 Archive leaderboard report
RGB-D Salient Object Detection STERE BiANet S-Measure 90.4 #10 of 14 Archive leaderboard report
RGB-D Salient Object Detection STERE BiANet max E-Measure 94.2 #10 of 14 Archive leaderboard report
RGB-D Salient Object Detection STERE BiANet max F-Measure 89.8 #10 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.

Methods

BAM

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