基于Convnextv2与纹理边缘引导的伪装目标检测

付家瑞,李兆飞,周豪,黄惟

Camouflaged object detection based on Convnextv2 and texture-edge guidance

Jiarui FU,Zhaofei LI,Hao ZHOU,Wei HUANG

表 2 CTEGAFNet与其他11种算法在NC4K和MICAI_TE上的对比结果

Tab.2 Comparison result of CTEGAFNet and other 11 methods in NC4K and MICAI_TE

网络 NC4K MICAI_TE Np/106 ${S_\alpha } $ ${F_\beta ^{\omega}}$ ${E_\phi }$ ${\mathrm{MAE}}$ ${S_\alpha } $ ${F_\beta ^{\omega}} $ ${E_\phi } $ ${\mathrm{MAE}} $ MSCAF 0.887 0.839 0.935 0.032 0.890 0.819 0.946 0.014 28.33 SARNet 0.886 0.842 0.937 0.032 0.888 0.811 0.944 0.014 44.79 FSNet 0.891 0.866 0.940 0.031 0.887 0.811 0.943 0.014 124.53 HitNet 0.870 0.825 0.921 0.039 0.886 0.822 0.955 0.014 24.53 SegMaR 0.841 0.781 0.905 0.046 0.874 0.782 0.920 0.019 68.04 SINet 0.808 0.723 0.871 0.058 0.678 0.387 0.624 0.052 48.95 SINetV2 0.847 0.770 0.903 0.048 0.733 0.508 0.739 0.038 26.98 C2FNet 0.838 0.762 0.897 0.049 0.867 0.776 0.933 0.019 26.30 BGNet 0.851 0.788 0.907 0.044 0.725 0.520 0.787 0.043 74.20 DGNet 0.857 0.784 0.911 0.042 0.872 0.779 0.928 0.018 21.02 ZoomNet 0.853 0.784 0.907 0.043 0.845 0.725 0.843 0.030 32.38 CTEGAFNet 0.900 0.859 0.940 0.028 0.895 0.827 0.953 0.013 92.94