S-Measure: 91.9Average MAE: 0.024
Papers with Code · CC BY-SA 4.0
RGB-D Salient Object Detection
RGB-D Salient object detection (SOD) aims at distinguishing the most visually distinctive objects or regions in a scene from the given RGB and Depth data. It has a wide range of applications, including video/image segmentation, object recognition, visual tracking, foreground maps evaluation, image retrieval, content-aware image editing, information discovery, photosynthesis, and weakly supervised semantic segmentation. Here, depth information plays an important complementary role in finding salient objects. Online benchmark: http://dpfan.net/d3netbenchmark.
<span style="color:grey; opacity: 0.6">( Image credit: Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks, TNNLS20 )</span>
논문
S-Measure: 85.0max E-Measure: 90.3max F-Measure: 85.1Average MAE: 0.064
S-Measure: 86.0max E-Measure: 90.9max F-Measure: 86.1Average MAE: 0.063
S-Measure: 88.2Average MAE: 0.044max F-Measure: 85.9max E-Measure: 91.9
S-Measure: 86.7Average MAE: 0.050max F-Measure: 84.9max E-Measure: 91.6
S-Measure: 94.2Average MAE: 0.016max F-Measure: 93.9max E-Measure: 97.1
S-Measure: 88.5Average MAE: 0.042max F-Measure: 88.1
S-Measure: 92.6Average MAE: 0.022max F-Measure: 91.4max E-Measure: 96.2
S-Measure: 87.5Average MAE: 0.051
S-Measure: 0.922
S-Measure: 94.3Average MAE: 0.018max E-Measure: 97.9max F-Measure: 94.0
S-Measure: 93.5Average MAE: 0.021max F-Measure: 90.9max E-Measure: 95.7
Average MAE: 0.043
S-Measure: 92.5Average MAE: 0.022max F-Measure: 91.6max E-Measure: 96.2
S-Measure: 87.5Average MAE: 0.059
S-Measure: 92.6Average MAE: 0.023max F-Measure: 91.7max E-Measure: 96.4