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... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
RGB-D Salient Object Detection DES DASNet S-Measure 90.8 # 8
Average MAE 0.023 # 5
max F-Measure 92.8 # 2
RGB-D Salient Object Detection NJU2K DASNet S-Measure 90.2 # 6
Average MAE 0.042 # 5
max F-Measure 91.1 # 3
RGB-D Salient Object Detection NLPR DASNet S-Measure 92.9 # 2
Average MAE 0.021 # 1
max F-Measure 92.9 # 1
RGB-D Salient Object Detection SSD 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 # 2
Average MAE 0.037 # 1
max F-Measure 91.5 # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet