</> Code with Papers by Syntology

Papers › Is Depth Really Necessary for Salient Object Detection?

Is Depth Really Necessary for Salient Object Detection?

30 May 2020arXiv:2006.00269archive 2025-07-28

Jia-Wei Zhao, Yifan Zhao, Jia Li, Xiaowu Chen

Salient object detection (SOD) is a crucial and preliminary task for many computer vision applications, which have made progress with deep CNNs. Most of the existing methods mainly rely on the RGB information to distinguish the salient objects, which faces difficulties in some complex scenarios. To solve this, many recent RGBD-based networks are proposed by adopting the depth map as an independent input and fuse the features with RGB information. Taking the advantages of RGB and RGBD methods, we propose a novel depth-aware salient object detection framework, which has following superior designs: 1) It only takes the depth information as training data while only relies on RGB information in the testing phase. 2) It comprehensively optimizes SOD features with multi-level depth-aware regularizations. 3) The depth information also serves as error-weighted map to correct the segmentation process. With these insightful designs combined, we make the first attempt in realizing an unified depth-aware framework with only RGB information as input for inference, which not only surpasses the state-of-the-art performances on five public RGB SOD benchmarks, but also surpasses the RGBD-based methods on five benchmarks by a large margin, while adopting less information and implementation light-weighted. The code and model will be publicly available.

PaperPDFCode

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

Code

JiaweiZhao-git/DASNet pytorchApache-2.0 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

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
RGB-D Salient Object Detection DES DASNet Average MAE 0.023 #12 of 13 Archive leaderboard report
RGB-D Salient Object Detection DES DASNet S-Measure 90.8 #12 of 13 Archive leaderboard report
RGB-D Salient Object Detection DES DASNet max F-Measure 92.8 #12 of 13 Archive leaderboard report
RGB-D Salient Object Detection NJU2K DASNet Average MAE 0.042 #13 of 27 Archive leaderboard report
RGB-D Salient Object Detection NJU2K DASNet S-Measure 90.2 #13 of 27 Archive leaderboard report
RGB-D Salient Object Detection NJU2K DASNet max F-Measure 91.1 #13 of 27 Archive leaderboard report
RGB-D Salient Object Detection NLPR DASNet Average MAE 0.021 #4 of 14 Archive leaderboard report
RGB-D Salient Object Detection NLPR DASNet S-Measure 92.9 #4 of 14 Archive leaderboard report
RGB-D Salient Object Detection NLPR DASNet max F-Measure 92.9 #4 of 14 Archive leaderboard report
RGB-D Salient Object Detection RGBD135 DASNet Average MAE 0.042 #1 of 5 Archive leaderboard report
RGB-D Salient Object Detection RGBD135 DASNet S-Measure 88.5 #1 of 5 Archive leaderboard report
RGB-D Salient Object Detection RGBD135 DASNet max F-Measure 88.1 #1 of 5 Archive leaderboard report
RGB-D Salient Object Detection STERE DASNet Average MAE 0.037 #4 of 14 Archive leaderboard report
RGB-D Salient Object Detection STERE DASNet S-Measure 91.0 #4 of 14 Archive leaderboard report
RGB-D Salient Object Detection STERE DASNet max F-Measure 91.5 #4 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