基于全局相关语义重要性的语义压缩算法
李勇,刘志强,田茂幸,贾松霖

Semantic compression algorithm based on global correlated semantic importance
Yong LI,Zhiqiang LIU,Maoxing TIAN,Songlin JIA
表 1 不同压缩算法在STL-10数据集中的性能测试结果
Tab.1 Performance testing results of different compression algorithms in STL-10 dataset
算法$\tau = 0.98 $$\tau = 0.90 $$\tau = 0.80 $$\tau = 0.60 $
AccprF1AccprF1AccprF1AccprF1
本研究0.810.820.810.810.940.940.940.940.950.950.950.950.960.960.960.96
文献[25]、[28]0.700.840.700.700.900.920.900.910.930.930.930.930.940.950.940.94
随机压缩0.540.600.540.480.630.790.630.610.790.860.790.770.910.920.910.91