Papers › Recursive Contour Saliency Blending Network for Accurate Salient Object Detection

Recursive Contour Saliency Blending Network for Accurate Salient Object Detection

28 May 2021arXiv:2105.13865archive 2025-07-28

Yi Ke Yun, Takahiro Tsubono

Contour information plays a vital role in salient object detection. However, excessive false positives remain in predictions from existing contour-based models due to insufficient contour-saliency fusion. In this work, we designed a network for better edge quality in salient object detection. We proposed a contour-saliency blending module to exchange information between contour and saliency. We adopted recursive CNN to increase contour-saliency fusion while keeping the total trainable parameters the same. Furthermore, we designed a stage-wise feature extraction module to help the model pick up the most helpful features from previous intermediate saliency predictions. Besides, we proposed two new loss functions, namely Dual Confinement Loss and Confidence Loss, for our model to generate better boundary predictions. Evaluation results on five common benchmark datasets reveal that our model achieves competitive state-of-the-art performance.

PaperPDFCode

Code

BarCodeReader/RCSB-PyTorch officialmentioned in paperpytorch 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 DetectionSalient Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Salient Object Detection DUT-OMRON RCSB E-measure 0.856 #8 of 8 Archive leaderboard report
Salient Object Detection DUT-OMRON RCSB MAE 0.045 #8 of 8 Archive leaderboard report
Salient Object Detection DUT-OMRON RCSB S-measure 0.820 #8 of 8 Archive leaderboard report
Salient Object Detection DUT-OMRON RCSB max_F1 0.810 #8 of 8 Archive leaderboard report
Salient Object Detection DUTS-TE RCSB E-measure 0.903 #8 of 8 Archive leaderboard report
Salient Object Detection DUTS-TE RCSB MAE 0.034 #8 of 8 Archive leaderboard report
Salient Object Detection DUTS-TE RCSB Smeasure 0.878 #8 of 8 Archive leaderboard report
Salient Object Detection DUTS-TE RCSB max_F1 0.889 #8 of 8 Archive leaderboard report
Salient Object Detection ECSSD RCSB E-measure 0.923 #9 of 10 Archive leaderboard report
Salient Object Detection ECSSD RCSB MAE 0.033 #9 of 10 Archive leaderboard report
Salient Object Detection ECSSD RCSB S-measure 0.921 #9 of 10 Archive leaderboard report
Salient Object Detection ECSSD RCSB max_F1 0.945 #9 of 10 Archive leaderboard report
Salient Object Detection HKU-IS RCSB E-measure 0.954 #7 of 9 Archive leaderboard report
Salient Object Detection HKU-IS RCSB MAE 0.027 #7 of 9 Archive leaderboard report
Salient Object Detection HKU-IS RCSB S-measure 0.918 #7 of 9 Archive leaderboard report
Salient Object Detection HKU-IS RCSB max_F1 0.938 #7 of 9 Archive leaderboard report
Salient Object Detection PASCAL-S RCSB E-measure 0.853 #9 of 10 Archive leaderboard report
Salient Object Detection PASCAL-S RCSB MAE 0.059 #9 of 10 Archive leaderboard report
Salient Object Detection PASCAL-S RCSB S-measure 0.854 #9 of 10 Archive leaderboard report
Salient Object Detection PASCAL-S RCSB max_F1 0.875 #9 of 10 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