</> Code with Papers by Syntology

Papers › BTS-Net: Bi-directional Transfer-and-Selection Network For RGB-D Salient Object Detection

BTS-Net: Bi-directional Transfer-and-Selection Network For RGB-D Salient Object Detection

5 Apr 2021arXiv:2104.01784archive 2025-07-28

Wenbo Zhang, Yao Jiang, Keren Fu, Qijun Zhao

Depth information has been proved beneficial in RGB-D salient object detection (SOD). However, depth maps obtained often suffer from low quality and inaccuracy. Most existing RGB-D SOD models have no cross-modal interactions or only have unidirectional interactions from depth to RGB in their encoder stages, which may lead to inaccurate encoder features when facing low quality depth. To address this limitation, we propose to conduct progressive bi-directional interactions as early in the encoder stage, yielding a novel bi-directional transfer-and-selection network named BTS-Net, which adopts a set of bi-directional transfer-and-selection (BTS) modules to purify features during encoding. Based on the resulting robust encoder features, we also design an effective light-weight group decoder to achieve accurate final saliency prediction. Comprehensive experiments on six widely used datasets demonstrate that BTS-Net surpasses 16 latest state-of-the-art approaches in terms of four key metrics.

PaperPDFCode

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

Code

zwbx/BTS-Net officialmentioned 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

DecoderObject DetectionRGB-D Salient Object DetectionSaliency PredictionSalient Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
RGB-D Salient Object Detection DES BTS-Net Average MAE 0.018 #2 of 13 Archive leaderboard report
RGB-D Salient Object Detection DES BTS-Net S-Measure 94.3 #2 of 13 Archive leaderboard report
RGB-D Salient Object Detection DES BTS-Net max E-Measure 97.9 #2 of 13 Archive leaderboard report
RGB-D Salient Object Detection DES BTS-Net max F-Measure 94.0 #2 of 13 Archive leaderboard report
RGB-D Salient Object Detection LFSD BTS-Net Average MAE 0.07 #2 of 8 Archive leaderboard report
RGB-D Salient Object Detection LFSD BTS-Net S-Measure 86.7 #2 of 8 Archive leaderboard report
RGB-D Salient Object Detection LFSD BTS-Net max E-Measure 90.6 #2 of 8 Archive leaderboard report
RGB-D Salient Object Detection LFSD BTS-Net max F-Measure 87.4 #2 of 8 Archive leaderboard report
RGB-D Salient Object Detection NJU2K BTS-Net Average MAE 0.036 #3 of 27 Archive leaderboard report
RGB-D Salient Object Detection NJU2K BTS-Net S-Measure 92.1 #3 of 27 Archive leaderboard report
RGB-D Salient Object Detection NJU2K BTS-Net max E-Measure 95.4 #3 of 27 Archive leaderboard report
RGB-D Salient Object Detection NJU2K BTS-Net max F-Measure 92.4 #3 of 27 Archive leaderboard report
RGB-D Salient Object Detection SIP BTS-Net Average MAE 0.044 #3 of 16 Archive leaderboard report
RGB-D Salient Object Detection SIP BTS-Net S-Measure 89.6 #3 of 16 Archive leaderboard report
RGB-D Salient Object Detection SIP BTS-Net max E-Measure 93.3 #3 of 16 Archive leaderboard report
RGB-D Salient Object Detection SIP BTS-Net max F-Measure 90.1 #3 of 16 Archive leaderboard report
RGB-D Salient Object Detection STERE BTS-Net Average MAE 0.038 #2 of 14 Archive leaderboard report
RGB-D Salient Object Detection STERE BTS-Net S-Measure 91.5 #2 of 14 Archive leaderboard report
RGB-D Salient Object Detection STERE BTS-Net max E-Measure 94.9 #2 of 14 Archive leaderboard report
RGB-D Salient Object Detection STERE BTS-Net max F-Measure 91.1 #2 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