Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Is Depth Really Necessary for Salient Object Detection?

About

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.

Jiawei Zhao, Yifan Zhao, Jia Li, Xiaowu Chen• 2020

Related benchmarks

TaskDatasetResultRank
Salient Object DetectionDUTS (test)
M (MAE)0.034
302
RGB-D Salient Object DetectionSTERE
S-measure (Sα)0.91
198
Salient Object DetectionPASCAL-S (test)
MAE0.064
149
Salient Object DetectionHKU-IS (test)
MAE0.027
137
Salient Object DetectionDUT-OMRON
MAE0.05
120
Salient Object DetectionECSSD (test)
S-measure (Sa)92.7
104
RGBD Saliency DetectionDES
S-measure0.908
102
Salient Object DetectionDUT-OMRON (test)
MAE0.05
92
Saliency Object DetectionSIP
F_beta Score0.9
79
Saliency DetectionNJUD (test)
MAE0.042
68
Showing 10 of 22 rows

Other info

Follow for update