S-Measure: 90.4Average MAE: 0.037
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: 90.8Average MAE: 0.041max F-Measure: 90.3max E-Measure: 94.2
S-Measure: 90.4Average MAE: 0.043max F-Measure: 89.8max E-Measure: 94.2
S-Measure: 86.7Average MAE: 0.07max E-Measure: 90.6max F-Measure: 87.4
S-Measure: 90.8Average MAE: 0.039max F-Measure: 88.9max E-Measure: 94.1
S-Measure: 87.9Average MAE: 0.051max F-Measure: 87.4max E-Measure: 92.5
S-Measure: 90.5Average MAE: 0.042max F-Measure: 90.1max E-Measure: 94.6
S-Measure: 89.9Average MAE: 0.046max F-Measure: 89.1max E-Measure: 93.8
S-Measure: 90.7Average MAE: 0.035max F-Measure: 90.0max E-Measure: 94.3
S-Measure: 90.3Average MAE: 0.039
S-Measure: 91.5max E-Measure: 95.0max F-Measure: 93.8Average MAE: 0.032
S-Measure: 91.0Average MAE: 0.037max F-Measure: 91.5
S-Measure: 89.2max E-Measure: 94.9max F-Measure: 90.0Average MAE: 0.046
S-Measure: 90.4max E-Measure: 94.4max F-Measure: 91.5Average MAE: 0.040