Skip to main content

Table 2 Ablation study of the proposed method. Baseline denotes the results of 2D methods over all-focus images while Avg. denotes the average results of 2D methods over all slices. Img. Input and Sal. Input denote the model trained only with RGB images and saliency maps, respectively. Reg. Loss and w/o Com. denote learning the model with the regression loss and without the proposed comparator, respectively. Bub. Test denotes testing the trained model as a bubble sorting algorithm. R-18 and SER-18 denote replacing the proposed encoder with well-designed architecture ResNet-18 [50] and SE-ResNet-18 [51], respectively

From: Are RGB-based salient object detection methods unsuitable for light field data?

Dataset Variant GCPA   F3Net   SCRN   BASNet CPD  
   \(\boldsymbol{\mathcal {M}}\downarrow \) \(\boldsymbol{\mathcal {E}}\uparrow \) \(\boldsymbol{\mathcal {M}}\downarrow \) \(\boldsymbol{\mathcal {E}}\uparrow \) \(\boldsymbol{\mathcal {M}}\downarrow \) \(\boldsymbol{\mathcal {E}}\uparrow \) \(\boldsymbol{\mathcal {M}}\downarrow \) \(\boldsymbol{\mathcal {E}}\uparrow \) \(\boldsymbol{\mathcal {M}}\downarrow \) \(\boldsymbol{\mathcal {E}}\uparrow \)
DUTLF Ours .045 .928 .045 .926 .048 .917 .048 .924 .046 .922
  Baseline .076 .874 .070 .878 .074 .868 .064 .894 .067 .885
  Avg. .085 .851 .084 .847 .088 .838 .082 .873 .084 .869
  Img. Input .054 .903 .056 .892 .061 .881 .058 .900 .055 .897
  Sal. Input .046 .926 .049 .920 .500 .913 .053 .918 .050 .914
  Reg. Loss .050 .919 .050 .917 .053 .910 .052 .918 .053 .914
  w/o Com. .049 .921 .053 .914 .053 .908 .057 .910 .054 .911
  Bub. Test .048 .923 .051 .915 .050 .914 .049 .923 .049 .914
  R-18 .049 .919 .047 .923 .051 .916 .054 .911 .048 .916
  SER-18 .048 .922 .047 .922 .049 .920 .051 .917 .048 .916
LFSD Ours .070 .882 .070 .892 .066 .900 .078 .888 .071 .892
  Baseline .098 .835 .105 .830 .087 .861 .084 .870 .089 .860
  Avg. .105 .829 .108 .820 .096 .843 .089 .857 .101 .839
  Img. Input .072 .882 .072 .878 .073 .885 .080 .878 .079 .882
  Sal. Input .070 .881 .073 .884 .067 .895 .087 .872 .074 .888
  Reg. Loss .076 .874 .079 .876 .070 .893 .080 .884 .074 .890
  w/o Com. .078 .871 .075 .884 .065 .897 .086 .873 .071 .891
  Bub. Test .076 .875 .081 .874 .066 .896 .079 .887 .073 .892
  R-18 .077 .875 .072 .884 .067 .892 .079 884 .075 .881
  SER-18 .076 .875 .073 .886 .066 .896 .079 .885 .073 .887