Is Depth Really Necessary for Salient Object Detection?

30 May 2020  ·  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.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
RGB-D Salient Object Detection DES DASNet S-Measure 90.8 # 10
Average MAE 0.023 # 10
max F-Measure 92.8 # 4
RGB-D Salient Object Detection NJU2K DASNet S-Measure 90.2 # 11
Average MAE 0.042 # 10
max F-Measure 91.1 # 6
RGB-D Salient Object Detection NLPR DASNet S-Measure 92.9 # 3
Average MAE 0.021 # 1
max F-Measure 92.9 # 1
RGB-D Salient Object Detection RGBD135 DASNet S-Measure 88.5 # 1
Average MAE 0.042 # 1
max F-Measure 88.1 # 1
RGB-D Salient Object Detection STERE DASNet S-Measure 91.0 # 3
Average MAE 0.037 # 2
max F-Measure 91.5 # 1

Methods


No methods listed for this paper. Add relevant methods here