基于卷积辅助自注意力的胸部疾病分类网络

张自然,李锵,关欣

Classification network for chest disease based on convolution-assisted self-attention

Ziran ZHANG,Qiang LI,Xin GUAN

表 9 不同胸部疾病分类网络的计算复杂度比较

Tab.9 Comparison of computational complexity of different chest disease classification network

网络 FLOPs/109 tinf/s 平均AUC SSGE[21] 17.74 0.059 0.830 CheXGCN[37] 17.86 0.061 0.826 PCAN[29] 3.92 0.054 0.830 Swin Trans[12] 4.37 0.013 0.837 CAWSNet 4.52 0.018 0.853