Papers › Siamese Network for RGB-D Salient Object Detection and Beyond

Siamese Network for RGB-D Salient Object Detection and Beyond

26 Aug 2020arXiv:2008.12134archive 2025-07-28

Keren Fu, Deng-Ping Fan, Ge-Peng Ji, Qijun Zhao, Jianbing Shen, Ce Zhu

Existing RGB-D salient object detection (SOD) models usually treat RGB and depth as independent information and design separate networks for feature extraction from each. Such schemes can easily be constrained by a limited amount of training data or over-reliance on an elaborately designed training process. Inspired by the observation that RGB and depth modalities actually present certain commonality in distinguishing salient objects, a novel joint learning and densely cooperative fusion (JL-DCF) architecture is designed to learn from both RGB and depth inputs through a shared network backbone, known as the Siamese architecture. In this paper, we propose two effective components: joint learning (JL), and densely cooperative fusion (DCF). The JL module provides robust saliency feature learning by exploiting cross-modal commonality via a Siamese network, while the DCF module is introduced for complementary feature discovery. Comprehensive experiments using five popular metrics show that the designed framework yields a robust RGB-D saliency detector with good generalization. As a result, JL-DCF significantly advances the state-of-the-art models by an average of ~2.0% (max F-measure) across seven challenging datasets. In addition, we show that JL-DCF is readily applicable to other related multi-modal detection tasks, including RGB-T (thermal infrared) SOD and video SOD, achieving comparable or even better performance against state-of-the-art methods. We also link JL-DCF to the RGB-D semantic segmentation field, showing its capability of outperforming several semantic segmentation models on the task of RGB-D SOD. These facts further confirm that the proposed framework could offer a potential solution for various applications and provide more insight into the cross-modal complementarity task.

PaperPDFCode

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

Code

kerenfu/JLDCF officialmentioned in papermentioned on GitHubpytorch report
taozh2017/RGBD-SODsurvey mentioned on GitHub 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

Object DetectionRGB Salient Object DetectionRGB-D Salient Object DetectionSalient Object DetectionSemantic Segmentationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
RGB-D Salient Object Detection DES JL-DCF* Average MAE 0.021 #6 of 13 Archive leaderboard report
RGB-D Salient Object Detection DES JL-DCF* S-Measure 93.6 #6 of 13 Archive leaderboard report
RGB-D Salient Object Detection DES JL-DCF* max E-Measure 97.5 #6 of 13 Archive leaderboard report
RGB-D Salient Object Detection DES JL-DCF* max F-Measure 92.9 #6 of 13 Archive leaderboard report
RGB-D Salient Object Detection NJU2K JL-DCF* Average MAE 0.040 #8 of 27 Archive leaderboard report
RGB-D Salient Object Detection NJU2K JL-DCF* S-Measure 91.1 #8 of 27 Archive leaderboard report
RGB-D Salient Object Detection NJU2K JL-DCF* max E-Measure 94.8 #8 of 27 Archive leaderboard report
RGB-D Salient Object Detection NJU2K JL-DCF* max F-Measure 91.3 #8 of 27 Archive leaderboard report
RGB-D Salient Object Detection NLPR JL-DCF* Average MAE 0.023 #6 of 14 Archive leaderboard report
RGB-D Salient Object Detection NLPR JL-DCF* S-Measure 92.6 #6 of 14 Archive leaderboard report
RGB-D Salient Object Detection NLPR JL-DCF* max E-Measure 96.4 #6 of 14 Archive leaderboard report
RGB-D Salient Object Detection NLPR JL-DCF* max F-Measure 91.7 #6 of 14 Archive leaderboard report
RGB-D Salient Object Detection SIP JL-DCF* Average MAE 0.046 #6 of 16 Archive leaderboard report
RGB-D Salient Object Detection SIP JL-DCF* S-Measure 89.2 #6 of 16 Archive leaderboard report
RGB-D Salient Object Detection SIP JL-DCF* max E-Measure 94.9 #6 of 16 Archive leaderboard report
RGB-D Salient Object Detection SIP JL-DCF* max F-Measure 90.0 #6 of 16 Archive leaderboard report
RGB-D Salient Object Detection STERE JL-DCF* Average MAE 0.039 #3 of 14 Archive leaderboard report
RGB-D Salient Object Detection STERE JL-DCF* S-Measure 91.1 #3 of 14 Archive leaderboard report
RGB-D Salient Object Detection STERE JL-DCF* max E-Measure 94.9 #3 of 14 Archive leaderboard report
RGB-D Salient Object Detection STERE JL-DCF* max F-Measure 90.7 #3 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